© 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. 19322
    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
    দিও
    -0.08
    agasy
    -0.08
    なる
    -0.07
    ardless
    -0.07
    онах
    -0.07
     //*
    -0.07
    า
    -0.07
    оть
    -0.07
    ിലെ
    -0.07
    ípio
    -0.07
    POSITIVE LOGITS
     that
    0.20
     regarding
    0.19
     involving
    0.19
     concernant
    0.18
     bezüglich
    0.15
     dotyczą
    0.15
     whereby
    0.15
    that
    0.15
     concerning
    0.15
     mengenai
    0.15
    Activations Density 0.094%

    No Known Activations