© 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. 111292
    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
     laten
    -0.08
    بی
    -0.08
    bracht
    -0.08
    COMMAND
    -0.08
     brengen
    -0.08
     lägga
    -0.08
    。”
    -0.07
    公开
    -0.07
    OBS
    -0.07
     intereses
    -0.07
    POSITIVE LOGITS
     Removing
    0.10
    hapus
    0.09
     freed
    0.09
     삭제
    0.09
    .prev
    0.09
     freeing
    0.09
     remov
    0.08
     removal
    0.08
     immin
    0.08
    ectomy
    0.08
    Activations Density 0.003%

    No Known Activations