Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

arXiv:2607.17425 · cs.LG · Submitted 2026-07-19 · Read on arXiv

cs.LG

Submitted: 2026-07-19

Updated: 2026-09-13

Code: https://github.com/aniket-desh/decoder-preserving-sae

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Sparsity — 26× in this paper · explained in 4 episodes
• Fidelity — 13× in this paper · explained in 2 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Reconstruction Error — 8× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Adam — 4× in this paper · explained in 2 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Distillation — 3× in this paper · explained in 2 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Sparse Autoencoders (SAEs) — 3× in this paper · explained in 3 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes

Sources

• BatchTopK Sparse Autoencoders
• Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need
• SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
• Task-Driven Dictionary Learning
• Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks