© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26412
    Prev
    Next
    INDEX
    Explanations

    statistical indicator variables

    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
     thiện
    -0.08
     resting
    -0.08
     Hilton
    -0.08
     astrolog
    -0.08
    энд
    -0.08
    ких
    -0.07
     richer
    -0.07
    545
    -0.07
     specifics
    -0.07
    ुत
    -0.07
    POSITIVE LOGITS
     fist
    0.08
     spur
    0.08
     interrup
    0.08
     �
    0.08
     Episodes
    0.07
     나타
    0.07
    /null
    0.07
     artır
    0.07
    0.07
     Па
    0.07
    Activations Density 0.001%

    No Known Activations