© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108245
    Prev
    Next
    INDEX
    Explanations

    Push or press buttons

    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
     compositions
    -0.08
     divina
    -0.08
     groom
    -0.08
     divine
    -0.08
     data
    -0.08
     readership
    -0.07
     passion
    -0.07
     retirement
    -0.07
     probabilities
    -0.07
     czy
    -0.07
    POSITIVE LOGITS
    踩
    0.10
     ketchup
    0.09
    	trigger
    0.09
    (Button
    0.09
    _MINUS
    0.09
    (atom
    0.09
    	btn
    0.08
    (btn
    0.08
     screwdriver
    0.08
    按钮
    0.08
    Activations Density 0.006%

    No Known Activations