© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 103243
    Prev
    Next
    INDEX
    Explanations

    discussing/examining

    np_max-act-logits · gemini-2.0-flash
    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
     можем
    -0.10
     precisamos
    -0.09
     necesitamos
    -0.09
     možemo
    -0.08
     हमारी
    -0.08
     Img
    -0.08
    <?=
    -0.08
    我们的
    -0.08
     possiamo
    -0.08
    我们
    -0.08
    POSITIVE LOGITS
     discusses
    0.25
     examines
    0.19
     подробно
    0.18
    章节
    0.17
     explores
    0.17
     besproken
    0.17
    介绍
    0.17
     chapters
    0.17
    讨论
    0.17
     vorgestellt
    0.17
    Activations Density 0.147%

    No Known Activations