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. 60882
    Prev
    Next
    INDEX
    Explanations

    for

    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
    _OK
    -0.07
    例
    -0.07
    500
    -0.07
     exempel
    -0.07
    995
    -0.07
     Novo
    -0.07
    科
    -0.07
    exception
    -0.07
    _checks
    -0.07
    ष
    -0.07
    POSITIVE LOGITS
    ání
    0.09
     선정
    0.08
    avorite
    0.08
     miscellaneous
    0.08
     geselect
    0.08
     всю
    0.07
    悠悠
    0.07
    átil
    0.07
    ategorical
    0.07
     Sexy
    0.07
    Activations Density 0.006%

    No Known Activations