© 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. 20257
    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
    不像
    -0.09
     faible
    -0.09
    =list
    -0.08
    Previously
    -0.08
    _=
    -0.08
     aando
    -0.08
    .These
    -0.08
     différente
    -0.08
    .Texture
    -0.08
     situação
    -0.08
    POSITIVE LOGITS
     cuad
    0.08
     Copa
    0.08
     Rachel
    0.08
     Persian
    0.08
    γραφ
    0.08
     Mary's
    0.08
     Audrey
    0.08
    -price
    0.08
     ഗ്ര
    0.08
    ಗ್ಗ
    0.08
    Activations Density 0.003%

    No Known Activations