© 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. 20789
    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
    外
    -0.09
     외
    -0.09
    외
    -0.09
    External
    -0.08
     дерева
    -0.08
     外
    -0.08
     dış
    -0.08
     externos
    -0.08
     außerhalb
    -0.08
    Outside
    -0.08
    POSITIVE LOGITS
     standard
    0.16
     standaard
    0.14
     standart
    0.14
    标准
    0.13
     standar
    0.13
    .standard
    0.13
     Standard
    0.13
    standard
    0.13
     стандарт
    0.13
     estándar
    0.12
    Activations Density 0.002%

    No Known Activations