© 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. 95016
    Prev
    Next
    INDEX
    Explanations

    Units of measurement

    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
     veloc
    -0.08
    Collections
    -0.08
     Osborne
    -0.08
     cavities
    -0.07
    Nathan
    -0.07
     فتح
    -0.07
    Nc
    -0.07
     Hurricanes
    -0.07
    ăto
    -0.07
     Filip
    -0.07
    POSITIVE LOGITS
     الواحد
    0.08
    마다
    0.08
     politica
    0.08
     dx
    0.07
     ascending
    0.07
    धान
    0.07
     tertentu
    0.07
     näh
    0.07
     zahlen
    0.07
     Politik
    0.07
    Activations Density 0.030%

    No Known Activations