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. 88201
    Prev
    Next
    INDEX
    Explanations

    AI prompts

    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
     کش
    -0.08
     한번
    -0.08
     kerran
    -0.08
    ેસ
    -0.08
     capital
    -0.08
     once
    -0.08
     જાણી
    -0.08
    [m
    -0.08
    演
    -0.07
    [\
    -0.07
    POSITIVE LOGITS
    crypted
    0.09
    encrypted
    0.08
    Deleted
    0.07
    inhua
    0.07
    Compatible
    0.07
    0.07
    imb
    0.07
    _deleted
    0.07
     encrypted
    0.07
     jų
    0.07
    Activations Density 0.003%

    No Known Activations