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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77514
    Prev
    Next
    INDEX
    Explanations

    com

    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
    meter
    -0.09
    此同时
    -0.09
     inta
    -0.08
    _ascii
    -0.08
    ASCII
    -0.08
    -upper
    -0.08
    -picture
    -0.08
    agonal
    -0.08
    मर
    -0.08
    meters
    -0.07
    POSITIVE LOGITS
     Dar
    0.09
    .jsdelivr
    0.08
     faker
    0.08
    }{
    0.07
     kommer
    0.07
     signing
    0.07
    .demo
    0.07
     Ein
    0.07
     aktuell
    0.07
    лен
    0.07
    Activations Density 0.001%

    No Known Activations