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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11837
    Prev
    Next
    INDEX
    Explanations

    Media companies, television

    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
    试玩
    -0.09
    VAT
    -0.08
    ట్ల
    -0.08
    提示
    -0.08
    GPU
    -0.07
    Arduino
    -0.07
     wybor
    -0.07
    安装
    -0.07
    Solver
    -0.07
     mechanic
    -0.07
    POSITIVE LOGITS
     콘텐츠
    0.09
     составля
    0.08
     Reven
    0.08
    'exploitation
    0.08
    /content
    0.08
     revenues
    0.08
     MSNBC
    0.08
     synd
    0.07
    retain
    0.07
     Lowell
    0.07
    Activations Density 0.025%

    No Known Activations