© 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. 3-RESID-POST-AA
    11. 12884
    Prev
    Next
    INDEX
    Explanations

    entry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enlight
    -0.09
    cession
    -0.07
    ygyny
    -0.07
     io
    -0.07
    Transportation
    -0.07
     carved
    -0.07
    De
    -0.07
     ص
    -0.07
     deception
    -0.07
    HTTPS
    -0.07
    POSITIVE LOGITS
     klink
    0.08
    orderen
    0.08
     Vital
    0.08
    קור
    0.08
     Tand
    0.08
     jab
    0.08
     rápida
    0.07
     contaminants
    0.07
     चाल
    0.07
     offending
    0.07
    Activations Density 0.002%

    No Known Activations