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. 55983
    Prev
    Next
    INDEX
    Explanations

    tang

    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
    Wil
    -0.08
     Ho
    -0.08
    PATH
    -0.08
     ms
    -0.08
     agile
    -0.08
    Ho
    -0.08
     tsis
    -0.07
    同行
    -0.07
    .selenium
    -0.07
     gost
    -0.07
    POSITIVE LOGITS
     champagne
    0.08
    각
    0.08
     சே
    0.07
    yat
    0.07
    dur
    0.07
     Ball
    0.07
    over
    0.07
     цвет
    0.07
     wal
    0.07
     worthy
    0.07
    Activations Density 0.005%

    No Known Activations