© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96195
    Prev
    Next
    INDEX
    Explanations

    А

    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
     Кон
    -0.09
     constructeur
    -0.08
     पुर
    -0.08
     konstruk
    -0.08
    ya
    -0.08
     кон
    -0.08
     સંપ
    -0.07
     নির্ম
    -0.07
     modify
    -0.07
     നിർമ്മ
    -0.07
    POSITIVE LOGITS
    кту
    0.13
    .Background
    0.08
     hinsichtlich
    0.08
    БУ
    0.07
    ਜ
    0.07
    بارات
    0.07
    جوی
    0.07
    .DELETE
    0.07
     commodo
    0.07
    .accounts
    0.07
    Activations Density 0.000%

    No Known Activations