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. 49339
    Prev
    Next
    INDEX
    Explanations

    Out of place

    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
    osm
    -0.08
    涨
    -0.08
    onso
    -0.07
     Saat
    -0.07
     Kay
    -0.07
    ve
    -0.07
     improving
    -0.07
     достаточно
    -0.07
    .Property
    -0.07
    .points
    -0.07
    POSITIVE LOGITS
     shouldn
    0.09
    Unexpected
    0.09
     lone
    0.08
     eigentlich
    0.08
     않
    0.08
     উচিত
    0.08
     unnatural
    0.08
     चाहिए
    0.08
    Should
    0.08
    erweise
    0.07
    Activations Density 0.036%

    No Known Activations