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. 119649
    Prev
    Next
    INDEX
    Explanations

    code related characters

    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
     Horizons
    -0.09
    浮
    -0.08
     horizon
    -0.08
     horizons
    -0.08
    .isnan
    -0.07
     pien
    -0.07
    adai
    -0.07
    brief
    -0.07
     quede
    -0.07
    然
    -0.07
    POSITIVE LOGITS
    :nth
    0.09
    nth
    0.08
    ibling
    0.08
    accordion
    0.08
    Nested
    0.08
    svg
    0.08
     arrangement
    0.08
     Carpet
    0.07
    nested
    0.07
    邻
    0.07
    Activations Density 0.003%

    No Known Activations