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. 53123
    Prev
    Next
    INDEX
    Explanations

    judgment/assessment

    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
    ーパ
    -0.09
    .take
    -0.07
    Instit
    -0.07
    layan
    -0.07
    撮
    -0.07
    ٽر
    -0.07
     insights
    -0.07
    rr
    -0.07
    Rol
    -0.07
     syncing
    -0.07
    POSITIVE LOGITS
    /logo
    0.08
     aanbevel
    0.08
     merr
    0.08
     overdue
    0.08
    алай
    0.08
    /logger
    0.08
    LAST
    0.08
     demás
    0.08
     Scotch
    0.08
    _except
    0.08
    Activations Density 0.011%

    No Known Activations