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. 98436
    Prev
    Next
    INDEX
    Explanations

    Testing/Tests

    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
    ưở
    -0.07
    ầng
    -0.07
    ằng
    -0.07
    -0.07
    ーブル
    -0.07
    ίκ
    -0.07
    .scalablytyped
    -0.06
    بية
    -0.06
    яр
    -0.06
    ежде
    -0.06
    POSITIVE LOGITS
    测试
    0.77
     test
    0.74
     테스트
    0.73
     тест
    0.72
     ટેસ્ટ
    0.70
     ಪರೀಕ್ಷ
    0.69
     testen
    0.69
    _test
    0.68
     పరీక్ష
    0.68
     परीक्षण
    0.68
    Activations Density 0.858%

    No Known Activations