© 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. 71562
    Prev
    Next
    INDEX
    Explanations

    copyrighted

    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
    Negative Logits
     bumi
    -0.09
     scout
    -0.09
     tě
    -0.08
     scouts
    -0.08
     slightly
    -0.08
     reminiscent
    -0.08
     koliko
    -0.08
     grazing
    -0.08
    .fre
    -0.08
     fizi
    -0.07
    POSITIVE LOGITS
     premises
    0.08
     Propriet
    0.07
     préserver
    0.07
    作品
    0.07
     copyrighted
    0.07
    holder
    0.07
     Protected
    0.07
     ವಿವರ
    0.07
     nummers
    0.07
     syscall
    0.07
    Activations Density 0.005%

    No Known Activations