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. 130723
    Prev
    Next
    INDEX
    Explanations

    pl

    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
    化
    -0.07
    ib
    -0.07
     Kale
    -0.07
    격
    -0.07
     brace
    -0.07
    ake
    -0.07
    іза
    -0.07
     सभा
    -0.07
     PNG
    -0.07
     ಸಭ
    -0.07
    POSITIVE LOGITS
    aggi
    0.09
     addictions
    0.08
     puo
    0.08
     languages
    0.08
    ਿਆਂ
    0.08
     whose
    0.08
     sider
    0.08
    тарды
    0.08
    UNO
    0.08
    افر
    0.07
    Activations Density 0.000%

    No Known Activations