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. 119907
    Prev
    Next
    INDEX
    Explanations

    Dialogue

    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
     crit
    -0.08
    .gov
    -0.08
    issu
    -0.07
     тк
    -0.07
    _assets
    -0.07
    enta
    -0.07
    OTE
    -0.07
    OPER
    -0.07
    avas
    -0.07
    .gray
    -0.07
    POSITIVE LOGITS
     ``
    0.09
     smaller
    0.08
    ``
    0.08
     cells
    0.08
    Camel
    0.07
    ុ
    0.07
    DED
    0.07
    Bell
    0.07
    ಮ್ಮೆ
    0.07
     kleinere
    0.07
    Activations Density 0.000%

    No Known Activations