© 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. 31061
    Prev
    Next
    INDEX
    Explanations

    origin

    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
     Charl
    -0.07
     Caroline
    -0.07
    ve
    -0.07
    321
    -0.07
    主体
    -0.07
     Ka
    -0.07
    Ka
    -0.07
     Kre
    -0.07
     Tat
    -0.07
    ty
    -0.07
    POSITIVE LOGITS
     origins
    0.09
     возникновения
    0.09
     происх
    0.09
     belakang
    0.09
     Origin
    0.08
     Origins
    0.08
    گذاری
    0.08
    (origin
    0.08
    搞
    0.08
    Origin
    0.08
    Activations Density 0.019%

    No Known Activations