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. 75944
    Prev
    Next
    INDEX
    Explanations

    degree of separation

    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
     illegally
    -0.11
     loot
    -0.09
    倾
    -0.09
    非法
    -0.08
     peluang
    -0.08
    赚钱
    -0.08
     盈
    -0.08
     Profit
    -0.08
    收益
    -0.08
     ama
    -0.08
    POSITIVE LOGITS
    Shortest
    0.10
    -instance
    0.09
     délais
    0.09
     distances
    0.08
     dauert
    0.08
     shortest
    0.08
     धी
    0.08
     faudra
    0.08
    最长
    0.08
     सार्व
    0.08
    Activations Density 0.011%

    No Known Activations