© 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. 47812
    Prev
    Next
    INDEX
    Explanations

    pattern

    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
    nb
    -0.08
     USP
    -0.07
     combustion
    -0.07
     specialist
    -0.07
    fb
    -0.07
     realistically
    -0.07
     realistic
    -0.07
     رسمی
    -0.07
     CTA
    -0.07
     WINAPI
    -0.07
    POSITIVE LOGITS
    规律
    0.12
     pattern
    0.11
     trend
    0.11
    趋势
    0.10
    Pattern
    0.09
    Trend
    0.09
     Pattern
    0.09
     Patterns
    0.09
    _pattern
    0.09
    trend
    0.09
    Activations Density 0.018%

    No Known Activations