© 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. 78273
    Prev
    Next
    INDEX
    Explanations

    encoding

    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
    ющего
    -0.08
     Edison
    -0.08
     μεγάλο
    -0.08
     વરસાદ
    -0.08
    куля
    -0.08
     rains
    -0.07
     ekolog
    -0.07
     Ethan
    -0.07
    િયા
    -0.07
    大发电
    -0.07
    POSITIVE LOGITS
    hei
    0.08
     weighting
    0.07
    ary
    0.07
    アル
    0.07
     blitt
    0.07
     mer
    0.07
    Weight
    0.07
     홈페이지
    0.07
     weight
    0.07
    ಗೆ
    0.07
    Activations Density 0.000%

    No Known Activations