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. 111785
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, configurations

    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
    Basis
    -0.09
     Jonah
    -0.08
    Executed
    -0.08
     offspring
    -0.08
     perpendicular
    -0.08
    Weapon
    -0.07
     музыку
    -0.07
    rique
    -0.07
     الموس
    -0.07
    Wheel
    -0.07
    POSITIVE LOGITS
     localhost
    0.14
     URLs
    0.13
    服务器
    0.13
     URL
    0.12
     servers
    0.12
     uzak
    0.12
    -url
    0.12
    _url
    0.12
    _URL
    0.11
    'https
    0.11
    Activations Density 0.020%

    No Known Activations