© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29255
    Prev
    Next
    INDEX
    Explanations

    't

    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
    urement
    -0.08
     determinant
    -0.08
    Accumulator
    -0.08
     Hundred
    -0.08
     Calif
    -0.07
    Fred
    -0.07
     bouton
    -0.07
     cose
    -0.07
    ,"↵
    -0.07
     Pere
    -0.07
    POSITIVE LOGITS
     കഥാപാത്ര
    0.09
     Can't
    0.08
     sexual
    0.08
     inaan
    0.08
     असा
    0.08
     sexu
    0.08
     cannot
    0.08
    ungeons
    0.08
     콘텐츠
    0.08
     κοινων
    0.08
    Activations Density 0.006%

    No Known Activations