© 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. 11-RESID-POST-AA
    11. 94744
    Prev
    Next
    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    仍
    -0.08
     dyd
    -0.08
    গুলি
    -0.08
     rir
    -0.08
    �
    -0.08
    既
    -0.07
    且
    -0.07
    ので
    -0.07
    犬
    -0.07
     yards
    -0.07
    POSITIVE LOGITS
    /chart
    0.08
     nový
    0.08
     супер
    0.08
     neuf
    0.08
     обс
    0.07
    chart
    0.07
     Commander
    0.07
     obič
    0.07
     nueve
    0.07
     οργαν
    0.07
    Activations Density 0.000%

    No Known Activations