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. 11-RESID-POST-AA
    6. 60814
    Prev
    Next
    INDEX
    Explanations

    articles or news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    进去
    -0.10
    оту
    -0.08
     auss
    -0.08
    然后
    -0.08
    'époque
    -0.08
     generations
    -0.08
     behaved
    -0.07
    worked
    -0.07
     kip
    -0.07
    聊天
    -0.07
    POSITIVE LOGITS
     Babe
    0.08
     Athlete
    0.08
     Cyrus
    0.08
     Macintosh
    0.08
     più
    0.08
     Geographic
    0.08
     Economic
    0.08
     cumpl
    0.07
     Ath
    0.07
     Sharma
    0.07
    Activations Density 0.419%

    No Known Activations