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. 60726
    Prev
    Next
    INDEX
    Explanations

    studying

    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
     collided
    -0.09
     surrogate
    -0.09
    indt
    -0.08
     ″
    -0.07
     inicialmente
    -0.07
     erstmals
    -0.07
    (progress
    -0.07
     tiled
    -0.07
    ricos
    -0.07
    -times
    -0.07
    POSITIVE LOGITS
     Learn
    0.09
     memorize
    0.08
     brauche
    0.08
    法规
    0.08
     knowing
    0.08
     знать
    0.08
     learner
    0.07
     learn
    0.07
    _rules
    0.07
     یاد
    0.07
    Activations Density 0.030%

    No Known Activations