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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58302
    Prev
    Next
    INDEX
    Explanations

    Table separators

    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
    atay
    -0.08
    .Ribbon
    -0.08
     საკ
    -0.07
    াঙ্গ
    -0.07
    artu
    -0.07
     tanda
    -0.07
     pand
    -0.07
    hews
    -0.07
     bankruptcy
    -0.07
    ENTS
    -0.07
    POSITIVE LOGITS
     dadurch
    0.09
     umož
    0.07
     बढ़
    0.07
    ’une
    0.07
    deen
    0.07
     मजब
    0.07
    _mu
    0.07
    èche
    0.07
    减少
    0.07
    .Unity
    0.07
    Activations Density 0.072%

    No Known Activations