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. 15-RESID-POST-AA
    6. 19508
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we'd
    -0.08
    _wc
    -0.08
    ignite
    -0.07
    ${
    -0.07
    ւ
    -0.07
    (${
    -0.07
     We'd
    -0.07
     (${
    -0.07
    Doc
    -0.07
    fü
    -0.07
    POSITIVE LOGITS
    <Field
    0.08
     naman
    0.07
     както
    0.07
     ETF
    0.07
     **
    0.07
     ETFs
    0.07
     frequentemente
    0.07
    ETING
    0.07
    :↵↵
    0.07
    ///<
    0.07
    Activations Density 0.102%

    No Known Activations