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. 56160
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ###↵↵
    -0.07
     pay
    -0.07
     payable
    -0.07
    vá
    -0.07
    _requires
    -0.07
     enough
    -0.07
    stered
    -0.07
    edia
    -0.07
     Trait
    -0.07
     நோ
    -0.07
    POSITIVE LOGITS
    Scanner
    0.08
     shampoo
    0.08
     地
    0.08
     автомобилей
    0.08
    scanner
    0.07
     автомобиля
    0.07
     chl
    0.07
    我国
    0.07
    ంతో
    0.07
    CAB
    0.07
    Activations Density 0.006%

    No Known Activations