© 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. 17925
    Prev
    Next
    INDEX
    Explanations

    messaging platforms

    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
    Negative Logits
    playlist
    -0.11
    Playlist
    -0.10
     insh
    -0.10
     playlist
    -0.09
     yoo
    -0.09
    Bookmark
    -0.08
    арб
    -0.08
     ipin
    -0.08
     packet
    -0.08
    bookmark
    -0.08
    POSITIVE LOGITS
     Telegram
    0.12
     Signal
    0.12
     Matrix
    0.11
     Teams
    0.10
     Matter
    0.10
    .Matrix
    0.10
     Salsa
    0.10
     Semaphore
    0.10
     Elements
    0.10
     Discord
    0.10
    Activations Density 0.002%

    No Known Activations