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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130818
    Prev
    Next
    INDEX
    Explanations

    performance

    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
     незакон
    -0.08
    ẫ
    -0.08
    acious
    -0.07
    neje
    -0.07
    ulio
    -0.07
    872
    -0.07
    609
    -0.07
    704
    -0.06
    aciente
    -0.06
    irala
    -0.06
    POSITIVE LOGITS
     performance
    0.75
    Performance
    0.69
     Performance
    0.69
    performance
    0.68
     desempenho
    0.68
    性能
    0.65
     performances
    0.61
     الأداء
    0.59
    .performance
    0.59
     प्रदर्शन
    0.58
    Activations Density 0.382%

    No Known Activations