© 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. 21239
    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
    ?>
↵
↵
    -0.10
    чунин
    -0.10
    <|call|>
    -0.10
    Faʻ
    -0.10
     जनाएको
    -0.10
    земпля
    -0.10
    եմն
    -0.10
    相关阅读
    -0.09
    češ
    -0.09
    amiliar
    -0.09
    POSITIVE LOGITS
     by
    0.17
     -
    0.16
     oleh
    0.12
     &
    0.12
     By
    0.12
     |
    0.12
    by
    0.12
     with
    0.11
     ★
    0.11
     ||
    0.11
    Activations Density 0.028%

    No Known Activations