AI RESEARCH
Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE
arXiv CS.LG
•
ArXi:2605.17493v1 Announce Type: new Deep learning weather prediction models achieve remarkable predictive skill yet remain largely opaque: we know little about how they represent physical climate phenomena internally. Mechanistic interpretability through Sparse Autoencoders (SAEs) offers a principled route to decomposing these representations, but existing SAEs assume strictly linear feature superposition - a constraint ill-suited for the highly nonlinear atmospheric dynamics encoded in modern transformers. We.