© 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. 63303
    Prev
    Next
    INDEX
    Explanations

    seed

    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
     eenvoud
    -0.08
     rightly
    -0.08
     dozen
    -0.07
    chinen
    -0.07
    心得
    -0.07
    Peng
    -0.07
     ль
    -0.07
    .Text
    -0.07
    畅
    -0.07
    ně
    -0.07
    POSITIVE LOGITS
    ordinator
    0.08
     усил
    0.08
     Hrvats
    0.08
    irish
    0.08
     ern
    0.08
     repert
    0.07
     GIR
    0.07
     colegios
    0.07
     sustaining
    0.07
     scent
    0.07
    Activations Density 0.001%

    No Known Activations