SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization

Anyuan Zhuo, Shaohua Zhang, Yuan Lin, Pinyan Lu

SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization: 8 upvotes on Hugging Face Daily Papers, #20 of 32 papers on 2026-11-06. Day-by-day upvote history.

Upvotes over time

It had 5 upvotes by its first day, 6 upvotes by the next day, 8 upvotes by day 3, 8 upvotes by day 7, and has 8 now. It ranked #128 of 207 papers in its week and #190 of 340 in its month. Its code repository has 4 GitHub stars.

Mixture-of-Experts (MoE) models route each token to a few of many experts, yet what an individual expert is responsible for remains unsettled. Existing analyses count how often an expert is selected on domain-labeled corpora, an instrument that fixes the taxonomy in advance, stays coarse, and records selection rather than contribution. We instead study specialization in feature space by training a sparse autoencoder (SAE) on the output of an MoE layer. Since this output is a router-weighted sum of expert outputs and the SAE encoder is affine, the pre-activation of every latent decomposes exactly over the experts. Aggregated over a corpus, this gives each expert a dominant set of latents whose activation it principally drives. On layers 4, 30 and 46 of Qwen3-30B-A3B, contribution is far more concentrated than gating, most latents have only one or two dominators, and the overlap between dominant sets concentrates on a few expert pairs. Auto-interpreting these sets reveals a division of labor below coarse domains, with distinct experts for Java and front-end web code, or for geometry and for arithmetic and polynomials, while the coarse domains themselves take very unequal numbers of experts. Our SAEs and code are available at https://github.com/Bytedance-Seed/SAE-Interprets-MoE.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.