© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114113
    Prev
    Next
    INDEX
    Explanations

    importantes

    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
    へ
    -0.09
    貌
    -0.08
    Ledger
    -0.08
    തിരെ
    -0.08
    閲
    -0.08
    क्षा
    -0.07
     Cyl
    -0.07
    Howdy
    -0.07
    ူး
    -0.07
    ತಿಯ
    -0.07
    POSITIVE LOGITS
     incredible
    0.09
     bagus
    0.09
     cifras
    0.08
     dentro
    0.07
    avan
    0.07
     पहले
    0.07
     Af
    0.07
     Throughout
    0.07
     Chuck
    0.07
    AV
    0.07
    Activations Density 0.003%

    No Known Activations