© 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 EvalsExportsinterp-engineNEWAPI 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. 51392
    Prev
    Next
    INDEX
    Explanations

    say "con" words

    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
     prizes
    -0.09
     premios
    -0.08
     hoʻ
    -0.08
     premiums
    -0.08
    tribute
    -0.08
    ánchez
    -0.08
     diferenças
    -0.08
    difference
    -0.08
     Nat
    -0.08
    both
    -0.08
    POSITIVE LOGITS
     conc
    0.20
     concurrent
    0.16
     concur
    0.16
     concurrence
    0.16
     coc
    0.15
     cop
    0.15
     co
    0.13
    (con
    0.13
    	con
    0.13
     aligned
    0.13
    Activations Density 0.039%

    No Known Activations