© 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. 51140
    Prev
    Next
    INDEX
    Explanations

    say "sub"

    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
     diza
    -0.09
    १३
    -0.09
    १०
    -0.08
    १९
    -0.08
    १६
    -0.08
     बीच
    -0.08
     dificil
    -0.08
     आयोजना
    -0.08
     contempla
    -0.08
    २४
    -0.08
    POSITIVE LOGITS
    apply
    0.10
    norm
    0.10
    lim
    0.10
    sub
    0.10
     aplicar
    0.09
    script
    0.08
    char
    0.08
    zero
    0.08
    .apply
    0.08
    Apply
    0.08
    Activations Density 0.001%

    No Known Activations