Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56079
    Prev
    Next
    INDEX
    Explanations

    Math rate problems

    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
     sommer
    -0.09
    年度
    -0.09
     വീട
    -0.09
     Jahres
    -0.09
     Diet
    -0.08
    符
    -0.08
     vivienda
    -0.08
     entlang
    -0.08
    Kul
    -0.08
     sociedad
    -0.08
    POSITIVE LOGITS
     pauses
    0.10
    (rate
    0.09
     rates
    0.09
     stopwatch
    0.09
    rate
    0.09
    _seconds
    0.09
     rhythm
    0.09
    .rate
    0.09
     rate
    0.09
    paused
    0.09
    Activations Density 0.042%

    No Known Activations