© 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. 19-RESID-POST-AA
    11. 18267
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -down
    -0.08
    downs
    -0.08
    ially
    -0.08
    awai
    -0.08
    ngoing
    -0.08
    down
    -0.07
    ১
    -0.07
    ylene
    -0.07
    ination
    -0.07
    -going
    -0.07
    POSITIVE LOGITS
     équilibre
    0.10
     balans
    0.10
    ուստ
    0.10
     équilibr
    0.09
    ուզ
    0.09
     ચોક
    0.09
    מאכט
    0.09
    საქართველ
    0.08
     madaling
    0.08
     sogen
    0.08
    Activations Density 0.003%

    No Known Activations