© 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. 21484
    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
     explorar
    -0.15
     explorers
    -0.14
     Explor
    -0.14
    expl
    -0.14
     explor
    -0.14
     explorer
    -0.14
    探索
    -0.13
     exploração
    -0.13
     exploration
    -0.13
     exploring
    -0.13
    POSITIVE LOGITS
     username
    0.28
    用户名
    0.27
     handle
    0.27
    handle
    0.26
    Username
    0.25
     usernames
    0.25
    _username
    0.25
    username
    0.24
    .username
    0.24
     Username
    0.24
    Activations Density 0.013%

    No Known Activations