© 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. 44858
    Prev
    Next
    INDEX
    Explanations

    circle

    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
    üng
    -0.07
    ियन
    -0.07
    공
    -0.07
     wrapper
    -0.07
    WIN
    -0.07
     空
    -0.07
     Wrapper
    -0.07
    空
    -0.07
     Hone
    -0.07
    -0.07
    POSITIVE LOGITS
     inteira
    0.09
     minus
    0.09
     completo
    0.08
    ിച്ചത്
    0.08
     UIStoryboard
    0.08
     nasce
    0.08
    เทศ
    0.08
     fossem
    0.08
    minus
    0.08
    idaire
    0.08
    Activations Density 0.017%
    No Known Activations