© 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. 52185
    Prev
    Next
    INDEX
    Explanations

    en

    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
    Negative Logits
     âmbito
    -0.10
     forbindelse
    -0.09
    ITY
    -0.09
     Ligne
    -0.09
     Tem
    -0.09
     силу
    -0.09
     Falle
    -0.09
     مجال
    -0.09
     vertu
    -0.09
     консульт
    -0.09
    POSITIVE LOGITS
    red
    0.12
    yes
    0.11
    off
    0.11
    ciendo
    0.10
    mar
    0.10
    redo
    0.10
    mud
    0.10
    rej
    0.10
    m
    0.10
    pieces
    0.09
    Activations Density 0.005%

    No Known Activations