© 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. 23-RESID-POST-AA
    11. 50093
    Prev
    Next
    INDEX
    Explanations

    say letter word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Napoli
    -0.10
     व
    -0.10
    佐
    -0.09
     baccarat
    -0.09
     Vettel
    -0.09
     vito
    -0.09
     Rico
    -0.09
     MSC
    -0.08
     salsa
    -0.08
     Epstein
    -0.08
    POSITIVE LOGITS
     SW
    0.39
     LW
    0.38
    	bw
    0.38
    	pw
    0.37
     PW
    0.37
     MW
    0.37
     rw
    0.37
     CW
    0.37
     GW
    0.36
     lw
    0.36
    Activations Density 0.180%

    No Known Activations