© 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. 110464
    Prev
    Next
    INDEX
    Explanations

    ==

    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
     Stephanie
    -0.08
    随着
    -0.07
    Stephanie
    -0.07
     pineapple
    -0.07
    印度
    -0.07
    FT
    -0.07
     salesman
    -0.07
     unión
    -0.07
     Osman
    -0.07
    UAL
    -0.07
    POSITIVE LOGITS
     "__
    0.11
     natura
    0.08
    (main
    0.08
    #error
    0.07
    .Main
    0.07
    __":↵
    0.07
    Prelude
    0.07
     Boiler
    0.07
     '__
    0.07
     lin
    0.07
    Activations Density 0.001%

    No Known Activations