© 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 EvalsExportsAPI 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. 69917
    Prev
    Next
    INDEX
    Explanations

    technical procedures

    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
     orde
    -0.08
     المث
    -0.07
    寻找
    -0.07
    代理
    -0.07
     method
    -0.07
    eken
    -0.07
    _da
    -0.07
    TP
    -0.07
    while
    -0.07
    atta
    -0.07
    POSITIVE LOGITS
    .AF
    0.08
    0.08
     serrure
    0.08
     киш
    0.08
     AUTOM
    0.08
    Knife
    0.08
    (KEY
    0.07
    .CR
    0.07
     Norden
    0.07
     diversified
    0.07
    Activations Density 0.000%
    No Known Activations