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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18928
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     WHERE
    -0.08
    _POS
    -0.07
    _EL
    -0.07
    WHERE
    -0.07
     CGRect
    -0.06
    _HPP
    -0.06
    _lon
    -0.06
    CGRect
    -0.06
     HP
    -0.06
    H
    -0.06
    POSITIVE LOGITS
    씩
    0.21
     प्रत्येक
    0.20
     each
    0.19
    ,每
    0.19
    每
    0.18
     દરેક
    0.18
     ഓരോ
    0.18
     ప్రతి
    0.18
     bawat
    0.17
     თითო
    0.17
    Activations Density 0.089%

    No Known Activations