© 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. 51933
    Prev
    Next
    INDEX
    Explanations

    Arctic regions

    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
    _IMETHOD
    -0.09
    ERG
    -0.08
     tuna
    -0.08
    ijent
    -0.08
     flare
    -0.08
     vah
    -0.08
    З
    -0.08
     Depression
    -0.08
    ūs
    -0.08
     मानसिक
    -0.08
    POSITIVE LOGITS
     Bar
    0.11
    Green
    0.10
     Green
    0.10
    Bar
    0.09
    .ar
    0.09
     GREEN
    0.09
     Bars
    0.08
     Gro
    0.08
    green
    0.08
     green
    0.08
    Activations Density 0.003%

    No Known Activations