© 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. 670
    Prev
    Next
    INDEX
    Explanations

    public

    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
     მეთ
    -0.10
     بصورة
    -0.09
     ഏത
    -0.09
     ];
↵
    -0.09
     വേണ്ടി
    -0.09
     مخت
    -0.09
     أيضاً
    -0.09
     أيضا
    -0.09
     അര
    -0.09
     ბოლო
    -0.09
    POSITIVE LOGITS
     scientists
    0.08
     million
    0.08
     curl
    0.08
     curls
    0.07
     controversy
    0.07
    _)
    0.07
     heroes
    0.07
    -your
    0.07
     ceramic
    0.07
    (cors
    0.07
    Activations Density 0.265%

    No Known Activations