- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This work introduces ClasSAE that trains a SAE (sparse autoencoder) to jointly learn reconstruction and feature-class affinity matrix. Technically, ClasSAE presents three architectural variants and provides a theoretical analysis of agreement objective. Empirically, ClasSAE demonstrates improved class alignment, dictionary utilization, and reduced reconstruction fidelity. Qualitative example also show meaningful features.
Critical strengths
-
ClasSAE focus on an important practical problem in SAE i.e., aligning sparse autoencoder features with meaningful classes. This would reduce the need for post-hoc feature annotation and ease usage for interpretation and targeted interventions.
-
ClasSAE offers a flexible interface between sparse features and concepts. Learning feature-class affinity matrix can reconcile both shared features and multiple features representing single concept.
-
Empirically, ClasSAE show promising results on dictionary utilization, class prediction, and interventions.
Critical weaknesses
-
Reviewer's biggest concern is on fairness. Current comparison does not isolate the effect of supervision. Other works like G-SAE [1], AlignSAE [2] also provide supervision while there is no comparison between other methods who are also using supervison.
-
Also, the quantitative evaluation only happens on CLIP embeddings for ImageNet-1K, with only a single dictionary size and association budget.
[1] Measuring and Guiding Monosemanticity
[2] AlignSAE: Concept-Aligned Sparse Autoencoders
Questions for authors
-
How does ClasSAE compare with a BatchTopK SAE trained with an ordinary supervised classification head and a G-SAE-style guided objective, using the same labels?
-
Two metric definitions seem to be inconsistent with the reported values. If both predicted and reference class sets contain the top k classes, why do Table 2 precision and recall differ? Also, how can Table 3’s stated “gap between the top two class scores” be negative? Please clarify the implemented definitions and whether any results require correction.
4 comments
Response to Reviewer WoHc: Summary of Changes and Point-by-Point Answers (2/2)
W2. Single dataset, dictionary size and association budget
We agree that the quantitative evaluation is limited to CLIP ViT-L/14 on ImageNet-1k. To check that the findings do not hinge on one dictionary size and budget, Appendix H repeats a reduced benchmark at d=4096, ρ=20 (target L0=64), comparing Sup BatchTopK, ClassifSAE and ClasSAE Hard (single seed; Tables 10–14).
Table B: subset of Tables 10–14 (single seed). "Native" and "emp." rows are the same ClasSAE Hard model evaluated with trained M or with the post-hoc matrix.
| Model | Matrix / rule | FVE | F1 | Acc | TPP 600 | TPP PMI | Off-diag PMI |
|---|---|---|---|---|---|---|---|
| Sup BatchTopK | post-hoc / emp. | 0.710 | 0.450 | 0.653 | 0.457 | 0.440 | 0.043 |
| ClassifSAE | post-hoc / emp. | 0.669 | 0.682 | 0.584 | 0.364 | 0.318 | 0.104 |
| ClasSAE Hard | trained / native | 0.780 | 0.894 | 0.783 | 0.450 | 0.471 | 0.003 |
| ClasSAE Hard | post-hoc / emp. | 0.780 | 0.933 | 0.742 | 0.450 | 0.466 | 0.011 |
The main conclusions carry over: ClasSAE Hard has the best FVE, annotation faithfulness, classification accuracy, TPP PMI and collateral damage. As in the main experiments it is not the best on standard fixed-k TPP, where Sup BatchTopK is highest (0.484, 0.468, 0.457 at k=20, 200, 600 vs. 0.335, 0.466, 0.450; Table 13). Since these results are single-seed, we make no ranking claim there. Beyond this setting we have no quantitative results on other datasets or backbones, so we do not claim that the numbers generalize.
Q2. Metric definitions
We thank the reviewer for catching these two inconsistencies. In both cases the descriptions in the paper were imprecise, and the reported values are correct.
Precision vs. recall (Table 2). The sets are not "top-k classes" for a common k, which was the source of the confusion. Appendix C (Eq. 8–9) now gives the full procedure:
- Each feature has its own non-integer budget, derived from the post-hoc firing-rate matrix with a threshold (same procedure for baselines). Its claimed set is the top classes of its row, as many as its budget.
- The prediction set comes from the train-side matrix (trained M for ClasSAE) and the reference set from the test-side matrix, each with its own budget.
Precision and recall are therefore equal only when the two sets have equal size. This holds approximately for post-hoc rows (ClasSAE 0.910 vs. 0.906), but not for trained M, whose learned budgets are not tied to firing rates (0.766 vs. 0.889). Table 2 now reports both variants for every ClasSAE model.
Margin (Table 3). The caption was wrong, not the results. It now defines Margin as the mean difference between the true-class score and the highest-scoring incorrect-class score. It is signed, hence negative when the true class is not ranked first (BatchTopK: accuracy 0.002, margin -0.148). No results require correction.
We thank the reviewer again for the constructive feedback.
References
- Härle et al. Measuring and guiding monosemanticity. NeurIPS 2025 (Spotlight).
- Le Bail et al. Unveiling decision-making in LLMs for text classification: Extraction of influential and interpretable concepts with sparse autoencoders. arXiv:2506.23951, 2025.
- Yang et al. AlignSAE: Concept-Aligned Sparse Autoencoders. Transactions on Machine Learning Research, 2026. https://openreview.net/forum?id=I9UjKxW4nq
Thank you for the detailed response and additional experiments. The supervised baselines strengthen the evaluation, and the revised definitions resolve my concerns about precision/recall and the signed margin.
My main remaining concern is the classification comparison. Section 4 explicitly evaluates ClasSAE using its trained , while supervised baselines use a post-hoc matrix rather than their own trained classification heads. Could you also report Sup BatchTopK and ClassifSAE using those heads? The current comparison demonstrates the usefulness of ClasSAE’s annotation interface, but does not fully establish its classification advantage over ordinary supervised SAE training.
You raised an important point that helps clarify the purpose of the classification experiment. We do not claim that ClasSAE is superior to dedicated models trained for classification. The goal of the experiment is to validate the matrix M as a meaningful addition: if M captures real class structure, the same matrix that was built for annotation and editing should also work as a classifier with no extra training. The question is whether one model can offer reconstruction, classification and intervention quality at the same time, which in our experiments the supervised baselines do not provide. As requested, we report the baselines read out with their own trained classification heads (5 seeds, same data and settings as Table 3). We include these results to give a complete picture of the classification experiment, not to claim an advantage.
Table D: classification with each model's own readout (baselines: own trained head; ClasSAE: trained matrix M). ClasSAE rows are a subset of Table 3.
| Model | Readout | Acc | Acc Top 5 | Acc Top 10 | F1 | Margin |
|---|---|---|---|---|---|---|
| Sup BatchTopK | own head | 0.841±0.000 | 0.972±0.000 | 0.986±0.000 | 0.839±0.000 | 62.783±0.458 |
| ClassifSAE | own head | 0.800±0.018 | 0.958±0.007 | 0.977±0.004 | 0.797±0.018 | 41.723±8.325 |
| ClasSAE | trained M | 0.750±0.002 | 0.914±0.003 | 0.941±0.001 | 0.748±0.003 | 0.096±0.001 |
| ClasSAE Hard | trained M | 0.789±0.001 | 0.940±0.000 | 0.962±0.000 | 0.787±0.001 | 0.131±0.001 |
| ClasSAE L1 | trained M | 0.799±0.001 | 0.955±0.000 | 0.976±0.000 | 0.796±0.001 | 0.168±0.000 |
With their own heads, the supervised baselines reach equal or higher accuracy (Sup BatchTopK 0.841, ClassifSAE 0.800 vs. 0.750–0.799 for ClasSAE), and we make no claim of a classification advantage. Margins are not comparable across the two readouts: for the baselines it is a gap between unconstrained head logits, for ClasSAE a gap between bounded matrix scores. We have added these results, with the clarification, as a new appendix (Appendix J, Table 15), and revised Section 4 and the Conclusions so that our classification claims refer to the matrix readout rather than to classification in general.
We read the result as supporting the matrix, for two reasons:
- M is a strongly constrained readout and is still close. It is sparse and non-negative, so its decision depends only on which features are present, while the heads of the baselines are unconstrained real-valued weights that can also use negative evidence between features (and ClassifSAE classifies from a 64-dimensional bottleneck, Appendix D). ClasSAE Hard (0.789) and ClasSAE L1 (0.799) are within 0.011 and 0.001 of ClassifSAE (0.800), and within 0.052 and 0.042 of Sup BatchTopK. We take this as evidence that M reflects high-quality class structure, although we did not isolate which constraint matters most.
- Basic supervision does not give all qualities at once. The supervised baselines' accuracy comes with lower reconstruction (FVE 0.881 and 0.755 vs. 0.910 for ClasSAE Hard, Table 1), lower annotation faithfulness (F1 0.537 and 0.651 vs. 0.851, Table 2) and weaker editing (TPP PMI 0.200 and 0.404 vs. 0.469, Table 4, with more collateral damage, Table 6). ClasSAE Hard reaches competitive classification while keeping the other three.
Response to Reviewer WoHc: Summary of Changes and Point-by-Point Answers (1/2)
We thank the reviewer for the careful reading and for recognizing the practical value of aligning SAE features with meaningful classes, the flexible interface between sparse features and concepts, and the results on dictionary utilization, class prediction and interventions. Both main concerns, that the comparison does not isolate the effect of supervision and that the evaluation covers a single setting, led to changes: three supervised baselines (Sup BatchTopK, ClassifSAE [2], G-SAE [1]) now appear in all main experiments (Tables 1–9), a reduced benchmark at a smaller dictionary size and budget is reported in Appendix H, and the metric definitions were clarified (Appendix C, Table 3 caption). Tables here are subsets of the paper's tables. Numbers are 5-seed means unless stated. Table numbers refer to the revised paper (Tables 5–7 and 10–14 are new).
We now include Sup BatchTopK (BatchTopK + ordinary linear classification head), G-SAE [1] (the guided objective of Härle et al.) and ClassifSAE [2], with the same ImageNet labels, L0 ≈ 380 and protocol (Section 4 "Setup", Appendix D). Baselines are read out with the post-hoc matrix. "Emp." is the same empirical-PMI edit rule for all models, "native" is ClasSAE's own rule.
Table A: subset of Tables 1 (FVE), 2 (F1), 3 (Acc), 4 (TPP PMI) and 6 (off-diagonal, PMI).
On AlignSAE [3]: we investigated it, but its loss includes a value loss that depends on the structure of the LLM it is trained in, which we cannot mimic directly for CLIP vision embeddings. Without that term, its objective is very close to the supervised baselines we already include, so we did not add it as a separate baseline.