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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54721
    Prev
    Next
    INDEX
    Explanations

    Foreign conversation

    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
    lech
    -0.08
    	Set
    -0.08
    opri
    -0.08
     Nav
    -0.08
    	put
    -0.08
    	I
    -0.07
    	This
    -0.07
    .pr
    -0.07
    	assign
    -0.07
    	for
    -0.07
    POSITIVE LOGITS
     motto
    0.09
     dan
    0.08
     bisa
    0.08
     samh
    0.07
     sinful
    0.07
     outsiders
    0.07
     gracious
    0.07
     ella
    0.07
     ("%
    0.07
     topic
    0.07
    Activations Density 0.000%

    No Known Activations