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. 88357
    Prev
    Next
    INDEX
    Explanations

    fork

    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
    US
    -0.08
     Rules
    -0.08
     Years
    -0.07
    Years
    -0.07
     Users
    -0.07
    olf
    -0.07
    429
    -0.07
     And
    -0.07
     gelten
    -0.07
     veget
    -0.07
    POSITIVE LOGITS
     distant
    0.09
     convenient
    0.08
    -picker
    0.08
    <Task
    0.08
     pencils
    0.08
    Eta
    0.07
    antage
    0.07
     distante
    0.07
    zend
    0.07
    _picker
    0.07
    Activations Density 0.001%

    No Known Activations