Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19440
    Prev
    Next
    INDEX
    Explanations

    until

    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
     जानते
    -0.07
    _positions
    -0.07
    겼
    -0.07
    iiii
    -0.07
    ídios
    -0.07
    gol
    -0.07
    ,arg
    -0.07
     begeistert
    -0.07
    quire
    -0.07
    =true
    -0.07
    POSITIVE LOGITS
     либо
    0.14
     totdat
    0.13
     either
    0.12
     είτε
    0.12
     انتهاء
    0.12
     entweder
    0.12
     прекращ
    0.11
     until
    0.11
     Either
    0.11
    停止
    0.11
    Activations Density 0.015%

    No Known Activations