© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1373
    Prev
    Next
    INDEX
    Explanations

    War

    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
     Vega
    -0.08
     мис
    -0.08
    эс
    -0.08
    estimate
    -0.08
     అన్న
    -0.08
    itsa
    -0.07
    .elem
    -0.07
    to
    -0.07
    ESH
    -0.07
     נא
    -0.07
    POSITIVE LOGITS
     conscience
    0.08
     interne
    0.08
     turmoil
    0.08
    党
    0.08
    意见
    0.08
    argout
    0.08
     violently
    0.07
    荡
    0.07
     ernstige
    0.07
    agot
    0.07
    Activations Density 0.003%

    No Known Activations