© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95342
    Prev
    Next
    INDEX
    Explanations

    stream

    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
     Smartphones
    -0.08
     журнал
    -0.08
     Presented
    -0.07
    Сегодня
    -0.07
    /cgi
    -0.07
     Pū
    -0.07
     Today
    -0.07
     спект
    -0.07
    -fiction
    -0.07
    eso
    -0.07
    POSITIVE LOGITS
    _cover
    0.09
    Cover
    0.09
    cover
    0.08
    .headers
    0.08
    Chunk
    0.08
     cover
    0.08
    Aws
    0.08
    _header
    0.08
    _headers
    0.08
    努
    0.08
    Activations Density 0.002%

    No Known Activations