SOURCE-LINKED INTELLIGENCE

Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities. Understanding the internal computations that support these adaptations is therefore becoming increasingly important for continual model evolution. Sparse autoencoders (SAEs) provide interpretable feature dictionaries for residual-stream activations and sublayer outputs, but it remains unclear how state features and update features interact to produce downstream residual features. In this work, we focus on MLP updates as a first test case. We

Read original source ↗ Open in workspace

recordType

paper

region

Global