© 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. 15-RESID-POST-AA
    6. 16333
    Prev
    Next
    INDEX
    Explanations

    French

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terutama
    -0.10
    และ
    -0.09
    urtout
    -0.09
    以及
    -0.09
    そして
    -0.09
     વગેરે
    -0.09
     وغيرها
    -0.09
    ()));↵↵
    -0.09
     Especially
    -0.09
     Особенно
    -0.09
    POSITIVE LOGITS
    -là
    0.08
     seniors
    0.07
    SRC
    0.07
    category
    0.07
     sér
    0.07
    CUL
    0.07
     category
    0.07
    Cate
    0.07
     ça
    0.07
     Seniors
    0.07
    Activations Density 0.072%

    No Known Activations