© 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. 63425
    Prev
    Next
    INDEX
    Explanations

    ActionScript code

    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
     День
    -0.09
     respiratory
    -0.09
    .pose
    -0.08
     cranberry
    -0.08
     Brexit
    -0.08
     brain
    -0.08
     cerebral
    -0.08
     dotenv
    -0.08
     garlic
    -0.08
     vaginal
    -0.08
    POSITIVE LOGITS
    Dispose
    0.10
     Adobe
    0.09
     Sprite
    0.09
    Adobe
    0.09
     sprites
    0.09
    Sprite
    0.09
     Cocoa
    0.09
    .sulake
    0.09
     PIX
    0.09
    (sprite
    0.09
    Activations Density 0.008%

    No Known Activations