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

    Neuronpedia

    Jacobian LensNEW
    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. 19-RESID-POST-AA
    11. 20151
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	if
    -0.11
    !*\↵
    -0.11
     someplace
    -0.11
     бывают
    -0.11
     ਉਹ
    -0.11
    omething
    -0.11
     someday
    -0.10
     those
    -0.10
    ㅎㅎ
    -0.10
    	this
    -0.10
    POSITIVE LOGITS
     director
    0.12
     Director
    0.09
     superintendent
    0.09
     supervisor
    0.09
     principal
    0.09
     directeur
    0.08
     ನಿರ್ದೇಶ
    0.08
     directora
    0.08
     edition
    0.08
     main
    0.08
    Activations Density 0.313%

    No Known Activations