© 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. 23-RESID-POST-AA
    11. 49772
    Prev
    Next
    INDEX
    Explanations

    brand design and trademarks

    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
     contrairement
    -0.08
     counters
    -0.07
    ige
    -0.07
     voorzichtig
    -0.07
    .mm
    -0.07
     कप
    -0.07
     atte
    -0.07
    311
    -0.07
    al
    -0.07
    474
    -0.07
    POSITIVE LOGITS
     крит
    0.09
     проектов
    0.09
     определ
    0.09
     classrooms
    0.08
     releg
    0.08
    rit
    0.08
     риска
    0.08
     школы
    0.08
     школа
    0.08
     категория
    0.08
    Activations Density 0.000%

    No Known Activations