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. 7-RESID-POST-AA
    6. 131065
    Prev
    Next
    INDEX
    Explanations

    .Add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نموذج
    -0.08
     modello
    -0.07
    онч
    -0.07
     einzel
    -0.07
     BP
    -0.07
     unconscious
    -0.07
     κρί
    -0.07
    BP
    -0.07
     асоб
    -0.07
     somm
    -0.07
    POSITIVE LOGITS
     ciki
    0.09
     favoritos
    0.08
     readily
    0.07
     pores
    0.07
     reco
    0.07
     gist
    0.07
     Divine
    0.07
    Favor
    0.07
     Favor
    0.07
     Sparta
    0.07
    Activations Density 0.001%

    No Known Activations