© 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. 19667
    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
    оскольку
    -0.10
     eventually
    -0.09
    Furthermore
    -0.09
     eventualmente
    -0.08
     corresponde
    -0.08
    оста
    -0.08
     wiederum
    -0.08
     decorrer
    -0.08
     corresponding
    -0.08
     esteve
    -0.08
    POSITIVE LOGITS
     소개
    0.15
    介绍
    0.15
    紹介
    0.14
     description
    0.13
    简介
    0.12
     vorgestellt
    0.12
    介紹
    0.12
     mention
    0.11
     Introduction
    0.11
     Introdu
    0.11
    Activations Density 0.044%

    No Known Activations