© 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. 20766
    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
    107
    -0.08
     النس
    -0.08
    172
    -0.08
    753
    -0.07
    wise
    -0.07
     experiments
    -0.07
    -specific
    -0.07
    eled
    -0.07
     souffle
    -0.07
    inging
    -0.07
    POSITIVE LOGITS
     perceived
    0.09
     percepção
    0.08
    :X
    0.08
    (Open
    0.08
    :view
    0.08
    .OPEN
    0.08
    ್ರ
    0.08
    !.↵
    0.08
    :S
    0.08
     {↵
    0.08
    Activations Density 0.054%

    No Known Activations