© 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. 29526
    Prev
    Next
    INDEX
    Explanations

    Python, input validation

    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
    ीक
    -0.08
    _SYNC
    -0.07
    प्र
    -0.07
     teammate
    -0.07
     bekom
    -0.07
    _SK
    -0.07
    记
    -0.07
    _COR
    -0.07
    ícia
    -0.07
    ịch
    -0.07
    POSITIVE LOGITS
     dabar
    0.08
     sese
    0.08
    šanu
    0.08
     pide
    0.08
     waw
    0.08
     Nuk
    0.08
     привет
    0.08
     bst
    0.08
     вроде
    0.08
     ತಿಳಿಸಿದ್ದಾರೆ
    0.08
    Activations Density 0.010%

    No Known Activations