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. 120277
    Prev
    Next
    INDEX
    Explanations

    Image

    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
     Benton
    -0.07
    nas
    -0.07
    lane
    -0.07
    ULATION
    -0.07
     বিব
    -0.07
    	lp
    -0.07
     Roosevelt
    -0.07
    standig
    -0.07
    _TEXTURE
    -0.07
    	QString
    -0.07
    POSITIVE LOGITS
    Actions
    0.08
     tritur
    0.08
     philosophies
    0.08
    _actions
    0.08
     thou
    0.08
     actions
    0.07
     curse
    0.07
     chut
    0.07
     teas
    0.07
    Ey
    0.07
    Activations Density 0.001%

    No Known Activations