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

    Neuronpedia

    APICircuit 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. 11956
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
    -Sm
    -0.08
    Sm
    -0.08
    arme
    -0.08
     sorte
    -0.08
    ijing
    -0.07
    imerk
    -0.07
     работе
    -0.07
     date
    -0.07
    (sm
    -0.07
    _sm
    -0.07
    POSITIVE LOGITS
     ulu
    0.09
     আও
    0.08
     ಉತ್ತ
    0.08
     ಜನ
    0.08
     Mov
    0.08
    .proxy
    0.08
     folie
    0.07
     hardcore
    0.07
     heel
    0.07
     straat
    0.07
    Activations Density 0.006%

    No Known Activations