Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75932
    Prev
    Next
    INDEX
    Explanations

    cold weather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
     laboratory
    -0.08
    ange
    -0.08
     Cite
    -0.07
     ')
    -0.07
     ontst
    -0.07
     Laboratory
    -0.07
     malfunction
    -0.07
     laboratories
    -0.07
     marker
    -0.07
    POSITIVE LOGITS
     chilly
    0.11
     colder
    0.10
    裸体
    0.09
     chilling
    0.09
     barefoot
    0.09
     dangers
    0.09
     Danger
    0.08
     naked
    0.08
     uncovered
    0.08
    冷
    0.08
    Activations Density 0.066%

    No Known Activations