© 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 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. 64183
    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
    ैया
    -0.08
    792
    -0.08
    Mond
    -0.08
    ాయి
    -0.07
     sichere
    -0.07
    🔥
    -0.07
    Lose
    -0.07
     HG
    -0.07
    裕
    -0.07
    HG
    -0.07
    POSITIVE LOGITS
     Зак
    0.08
     fecha
    0.08
     vil
    0.08
     തമ്മ
    0.08
     Completed
    0.08
     Para
    0.07
     ഇവ
    0.07
     među
    0.07
     Orden
    0.07
     Fecha
    0.07
    Activations Density 0.001%

    No Known Activations