© 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. 23-RESID-POST-AA
    11. 6355
    Prev
    Next
    INDEX
    Explanations

    go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inci
    -0.08
    697
    -0.08
    nić
    -0.08
    ieso
    -0.08
    bere
    -0.08
    jie
    -0.08
     bảo
    -0.08
     harmony
    -0.07
    ouncycastle
    -0.07
    plugins
    -0.07
    POSITIVE LOGITS
     эпох
    0.08
     Tuesdays
    0.08
    天天看
    0.08
     зерк
    0.08
     револю
    0.08
    CD
    0.08
     Zeiten
    0.07
     цик
    0.07
    ednesdays
    0.07
     Nights
    0.07
    Activations Density 0.000%

    No Known Activations