© 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. 18244
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     around
    -0.08
    of
    -0.08
    /of
    -0.08
    ≈
    -0.08
    for
    -0.08
     tendência
    -0.08
    /...
    -0.07
    ~/
    -0.07
     total
    -0.07
    Exceeded
    -0.07
    POSITIVE LOGITS
     Odin
    0.10
     morts
    0.09
    Officer
    0.08
     Engeland
    0.08
     Nurse
    0.08
     Officers
    0.08
    orsa
    0.08
     Midtown
    0.08
     Inch
    0.08
     Rats
    0.08
    Activations Density 0.001%

    No Known Activations