© 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. 7-RESID-POST-AA
    11. 1124
    Prev
    Next
    INDEX
    Explanations

    terrace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ivory
    -0.08
     contest
    -0.07
     crystall
    -0.07
     bent
    -0.07
     alliance
    -0.07
    �
    -0.07
     swirl
    -0.07
     nejs
    -0.07
     Î
    -0.07
     whisk
    -0.07
    POSITIVE LOGITS
     desal
    0.09
     sto
    0.09
    顶部
    0.08
    （水
    0.08
    /y
    0.07
     सफ
    0.07
     يوم
    0.07
     Veronica
    0.07
    اي
    0.07
    了一
    0.07
    Activations Density 0.003%

    No Known Activations