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. 78640
    Prev
    Next
    INDEX
    Explanations

    be

    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
     UD
    -0.08
    .lr
    -0.07
     شم
    -0.07
     Télécharger
    -0.07
    Ux
    -0.07
     blast
    -0.07
    їв
    -0.07
     Gutenberg
    -0.07
     daun
    -0.07
    _ud
    -0.07
    POSITIVE LOGITS
     vär
    0.08
     മാറ
    0.08
     samp
    0.08
    _kel
    0.07
     பால
    0.07
     pont
    0.07
    ision
    0.07
    ('/:
    0.07
    olland
    0.07
     Kelvin
    0.07
    Activations Density 0.009%

    No Known Activations