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. 111685
    Prev
    Next
    INDEX
    Explanations

    multiple choice questions

    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
     Employee
    -0.10
    ぞ
    -0.08
     Delete
    -0.08
     Billboard
    -0.08
     Hyper
    -0.08
     teenager
    -0.08
    akyat
    -0.08
    Employer
    -0.08
    achat
    -0.08
    employee
    -0.08
    POSITIVE LOGITS
     sealing
    0.09
     кис
    0.08
     вина
    0.08
     gris
    0.08
     pur
    0.08
     �
    0.07
     oficina
    0.07
    _);↵↵
    0.07
     contexts
    0.07
     fecha
    0.07
    Activations Density 0.002%

    No Known Activations