© 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. 20923
    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
     ראשון
    -0.10
     ղ
    -0.10
     տեղ
    -0.09
     <-
    -0.09
     ҙ
    -0.09
    凤凰大
    -0.09
    俺去
    -0.09
    ←
    -0.09
    ընդ
    -0.09
    俺也
    -0.09
    POSITIVE LOGITS
     intric
    0.08
    ,
    0.07
    ،
    0.07
    .je
    0.07
     seguintes
    0.07
    <|reserved_200016|>
    0.06
     details
    0.06
     code
    0.06
    quest
    0.06
    Kenn
    0.06
    Activations Density 1.545%

    No Known Activations