© 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. 71439
    Prev
    Next
    INDEX
    Explanations

    structural engineering and seismic activity

    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
     Emoji
    -0.10
    Emoji
    -0.10
    emoji
    -0.09
     embarrassment
    -0.09
     Binance
    -0.09
    Spotify
    -0.09
     Spotlight
    -0.09
    .tsv
    -0.09
     настрой
    -0.09
     etiquette
    -0.09
    POSITIVE LOGITS
     seismic
    0.11
     stiffness
    0.11
     steel
    0.11
     FEM
    0.11
    施工
    0.10
     stiff
    0.10
     mortar
    0.09
     beton
    0.09
     deform
    0.09
     fracture
    0.09
    Activations Density 0.030%

    No Known Activations