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. 119277
    Prev
    Next
    INDEX
    Explanations

    data sizes (in bytes)

    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
    _depart
    -0.09
    _department
    -0.09
     crumble
    -0.08
    Departments
    -0.08
     sincere
    -0.08
     geographically
    -0.08
    Driving
    -0.08
    $scope
    -0.08
    Sports
    -0.08
    .Vertical
    -0.08
    POSITIVE LOGITS
     bytes
    0.16
     sizeof
    0.15
    (sizeof
    0.13
    bytes
    0.13
    offsetof
    0.13
    	sizeof
    0.12
    Bytes
    0.12
    	bytes
    0.12
    _BYTES
    0.12
    (bytes
    0.12
    Activations Density 0.013%

    No Known Activations