© 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. 99342
    Prev
    Next
    INDEX
    Explanations

    oping

    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
     realistic
    -0.09
     striving
    -0.08
     जित
    -0.08
     harsh
    -0.07
     ample
    -0.07
     réal
    -0.07
     विश्वास
    -0.07
     provision
    -0.07
     تعد
    -0.07
     realism
    -0.07
    POSITIVE LOGITS
     telesc
    0.09
     dividends
    0.09
    _EXPR
    0.09
    Ken
    0.08
    Beiträge
    0.08
     Toe
    0.08
    oodi
    0.08
     vegna
    0.08
     sums
    0.08
    Dividend
    0.08
    Activations Density 0.002%

    No Known Activations