© 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. 11-RESID-POST-AA
    11. 71444
    Prev
    Next
    INDEX
    Explanations

    MongoDB connection code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     empowers
    -0.08
     bricks
    -0.08
    (width
    -0.08
     punches
    -0.08
    washer
    -0.08
     Kick
    -0.07
    ,height
    -0.07
    length
    -0.07
    (height
    -0.07
     orden
    -0.07
    POSITIVE LOGITS
     asyncio
    0.09
     nejlepší
    0.09
    Avoid
    0.09
     Avoid
    0.08
    避免
    0.08
     éviter
    0.08
     Aurora
    0.08
    爱情
    0.08
     aşk
    0.08
     Acid
    0.08
    Activations Density 0.001%

    No Known Activations