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. 49073
    Prev
    Next
    INDEX
    Explanations

    numpy arrays

    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
     parish
    -0.09
    餐
    -0.09
     district
    -0.09
     rozh
    -0.09
    Pickup
    -0.08
     premises
    -0.08
    资
    -0.08
     tarot
    -0.08
    960
    -0.08
    _business
    -0.08
    POSITIVE LOGITS
     ndarray
    0.17
    .astype
    0.16
     dtype
    0.16
    .dtype
    0.15
    .ndarray
    0.15
    numpy
    0.14
     numpy
    0.14
    .numpy
    0.14
    (dtype
    0.14
    _dtype
    0.14
    Activations Density 0.021%

    No Known Activations