© 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. 70278
    Prev
    Next
    INDEX
    Explanations

    fraud

    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
    уется
    -0.07
    valuable
    -0.07
     FIRST
    -0.07
     കാര്യ
    -0.07
     يحتوي
    -0.07
    ugu
    -0.07
     estás
    -0.07
     notification
    -0.07
     efficiently
    -0.07
     necesitas
    -0.07
    POSITIVE LOGITS
    作弊
    0.12
     fraudulent
    0.11
     fict
    0.09
    .invalid
    0.09
     корруп
    0.09
    .cor
    0.09
     maling
    0.09
     artificially
    0.09
     adulter
    0.09
     delinc
    0.09
    Activations Density 0.031%

    No Known Activations