© 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. 26369
    Prev
    Next
    INDEX
    Explanations

    calibration and regression

    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
     हेत
    -0.08
    trian
    -0.08
    Eigen
    -0.08
     Hein
    -0.07
    暴
    -0.07
    Rear
    -0.07
    嫌
    -0.07
     sinister
    -0.07
     करण
    -0.07
     potente
    -0.07
    POSITIVE LOGITS
     corrections
    0.08
     sher
    0.08
     refurb
    0.08
     Corre
    0.08
     διο
    0.08
     Belle
    0.08
    --------------------------------
    0.07
     Lookup
    0.07
    .Task
    0.07
     Temple
    0.07
    Activations Density 0.000%

    No Known Activations