© 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. 110551
    Prev
    Next
    INDEX
    Explanations

    Percentage calculations

    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
    Intersect
    -0.08
     అభ
    -0.08
     Yin
    -0.07
    ,E
    -0.07
    ett
    -0.07
    Innov
    -0.07
    Cham
    -0.07
    Publicidade
    -0.07
    {}↵
    -0.07
    Bi
    -0.07
    POSITIVE LOGITS
     Gross
    0.08
     fuss
    0.08
     ～
    0.08
     Aron
    0.08
     sola
    0.08
     morbidity
    0.08
    ↵			↵
    0.07
     Addr
    0.07
     stupid
    0.07
     butt
    0.07
    Activations Density 0.037%

    No Known Activations