© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71426
    Prev
    Next
    INDEX
    Explanations

    minimum quantities

    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
     neat
    -0.08
    ைத்த
    -0.07
     masing
    -0.07
     위한
    -0.07
    sap
    -0.07
     bedo
    -0.07
     mua
    -0.07
     toko
    -0.07
     gratuit
    -0.07
     Geschmack
    -0.07
    POSITIVE LOGITS
    人在
    0.10
    数据显示
    0.10
     लोग
    0.10
     ljudi
    0.10
     используется
    0.09
     sprake
    0.09
    情况下
    0.09
     происходит
    0.09
     portion
    0.08
     사람들이
    0.08
    Activations Density 0.389%

    No Known Activations