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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 111804
    Prev
    Next
    INDEX
    Explanations

    tables, code, or steps

    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
    _outline
    -0.08
    kite
    -0.07
    ETE
    -0.07
    sar
    -0.07
     quadro
    -0.07
    gel
    -0.07
     Cah
    -0.07
    mediate
    -0.07
    mdi
    -0.07
    /work
    -0.07
    POSITIVE LOGITS
     задум
    0.09
     Chess
    0.08
    онь
    0.08
    рез
    0.07
     bất
    0.07
     Humanos
    0.07
     Oosten
    0.07
     tendencia
    0.07
    .atomic
    0.07
     тему
    0.07
    Activations Density 0.000%

    No Known Activations