© 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. 21427
    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
     sebag
    -0.08
     Etc
    -0.08
    有哪些
    -0.08
     intend
    -0.07
     via
    -0.07
     qanday
    -0.07
     haviam
    -0.07
     briefly
    -0.07
     қандай
    -0.07
    agara
    -0.07
    POSITIVE LOGITS
    ؟
    0.11
    ？
    0.10
    ?
    0.10
    )?
    0.10
     լավագույն
    0.10
     ավելի
    0.09
     საუკეთ
    0.09
    ？！
    0.09
    —they
    0.09
     हुँदा
    0.09
    Activations Density 0.004%

    No Known Activations