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. 49079
    Prev
    Next
    INDEX
    Explanations

    Relativity and physics

    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
    Experimental
    -0.08
    Internal
    -0.08
    .helper
    -0.08
     Israel
    -0.08
    .internal
    -0.08
     Experimental
    -0.08
     Iran
    -0.07
    _fig
    -0.07
    Inner
    -0.07
    _area
    -0.07
    POSITIVE LOGITS
     arriva
    0.09
    转换
    0.09
     convertible
    0.09
    ofy
    0.09
     entfer
    0.09
     परिव
    0.08
     arrivent
    0.08
    izziness
    0.08
    เครดิต
    0.08
     अध्यक्ष
    0.08
    Activations Density 0.001%

    No Known Activations