© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51992
    Prev
    Next
    INDEX
    Explanations

    say "aced"

    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
    -earned
    -0.09
    -man
    -0.08
    byn
    -0.08
     broad
    -0.08
    azon
    -0.08
    мун
    -0.08
    Zones
    -0.07
    qları
    -0.07
    vela
    -0.07
     barrios
    -0.07
    POSITIVE LOGITS
    aced
    0.13
    acing
    0.10
    acement
    0.09
    	line
    0.09
     line
    0.09
    aci
    0.09
     tracking
    0.08
    行
    0.08
     لائن
    0.08
    acado
    0.08
    Activations Density 0.001%

    No Known Activations