© 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 EvalsExportsinterp-engineNEWAPI 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. 22438
    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
    ijken
    -0.08
     pratiques
    -0.08
    uld
    -0.07
    puesta
    -0.07
    managed
    -0.07
    edoen
    -0.07
    (Screen
    -0.07
    uyen
    -0.07
    posta
    -0.07
    culas
    -0.07
    POSITIVE LOGITS
    _system
    0.12
     hệ
    0.11
     system
    0.11
     सिस्टम
    0.11
     сіст
    0.11
    System
    0.11
    .system
    0.11
     sistem
    0.10
     سیستم
    0.10
    系统
    0.10
    Activations Density 0.009%

    No Known Activations