© 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. 7-RESID-POST-AA
    11. 1243
    Prev
    Next
    INDEX
    Explanations

    把

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malawi
    -0.08
     Lagos
    -0.08
     Represents
    -0.08
     കല
    -0.08
     coughing
    -0.08
     Kun
    -0.08
     Hin
    -0.08
    omeje
    -0.07
     לאורך
    -0.07
     Henrik
    -0.07
    POSITIVE LOGITS
    即可
    0.08
    Land
    0.08
    by
    0.07
     intox
    0.07
     मग
    0.07
     PPT
    0.07
     diminishing
    0.07
     sweaty
    0.07
     draft
    0.07
     Land
    0.07
    Activations Density 0.006%

    No Known Activations