© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20225
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     zuiden
    -0.11
     foco
    -0.10
     proteção
    -0.10
     સુર
    -0.10
     보호
    -0.09
     zašt
    -0.09
    туруш
    -0.09
     защиты
    -0.09
     desember
    -0.09
     ვიდეო
    -0.09
    POSITIVE LOGITS
    DB
    0.13
    &eacute
    0.09
    db
    0.09
    oses
    0.08
    Db
    0.08
    Database
    0.08
    OS
    0.08
    arios
    0.08
    xdb
    0.08
    mongoose
    0.08
    Activations Density 0.001%

    No Known Activations