© 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. 70332
    Prev
    Next
    INDEX
    Explanations

    sage

    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
    éma
    -0.07
     Dar
    -0.07
     Kav
    -0.07
    atik
    -0.07
    mann
    -0.07
     Kik
    -0.07
    enta
    -0.07
     الإج
    -0.07
     kik
    -0.07
     عامل
    -0.07
    POSITIVE LOGITS
     Mari
    0.08
     tale
    0.07
     거
    0.07
    brush
    0.07
     disp
    0.07
     Magnus
    0.07
    驱
    0.07
    olian
    0.07
    傅
    0.07
    .feature
    0.07
    Activations Density 0.002%

    No Known Activations