© 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. 78269
    Prev
    Next
    INDEX
    Explanations

    place

    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
    हम
    -0.08
    �
    -0.07
    jun
    -0.07
     podr
    -0.07
    ಗೆ
    -0.07
     серв
    -0.07
     vitesse
    -0.07
     outlook
    -0.07
    odd
    -0.07
     ಅವ
    -0.07
    POSITIVE LOGITS
     taht
    0.08
    Oauth
    0.07
     ().
    0.07
     financière
    0.07
     reo
    0.07
    gp
    0.07
     determin
    0.07
    �
    0.07
    gc
    0.07
     Ortiz
    0.07
    Activations Density 0.006%

    No Known Activations