© 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. 19922
    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
     dazugeh
    -0.10
     dargest
    -0.09
    <|reserved_200000|>
    -0.08
     kawaida
    -0.08
    ைப்பட
    -0.07
     wybodaeth
    -0.07
    יוחד
    -0.07
     doce
    -0.07
    ואה
    -0.07
     jeito
    -0.07
    POSITIVE LOGITS
     regarding
    0.14
     whereby
    0.14
     بشأن
    0.14
     wherein
    0.13
     щодо
    0.12
     که
    0.12
     ਕਿ
    0.11
     ਜਿਸ
    0.11
     Which
    0.10
     waarbij
    0.10
    Activations Density 0.275%

    No Known Activations