© 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. 22237
    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
     თუ
    -0.10
     եթե
    -0.10
    ?,?,
    -0.10
    ятель
    -0.09
    ющей
    -0.09
    инград
    -0.09
    есед
    -0.09
    еннолет
    -0.09
    циях
    -0.09
     говоря
    -0.09
    POSITIVE LOGITS
    ing
    0.15
    s
    0.15
    wert
    0.14
    y
    0.13
    e
    0.12
    en
    0.11
    ed
    0.11
    eqert
    0.11
    d
    0.11
    iang
    0.11
    Activations Density 0.055%

    No Known Activations