© 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. 23-RESID-POST-AA
    11. 49099
    Prev
    Next
    INDEX
    Explanations

    cin

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sorted
    -0.09
     Jeremiah
    -0.08
    Sorted
    -0.08
     adaptée
    -0.08
    框
    -0.08
    פּ
    -0.08
     кет
    -0.07
     sorted
    -0.07
    ência
    -0.07
     georgan
    -0.07
    POSITIVE LOGITS
     اخت
    0.08
     ultra
    0.08
    house
    0.07
    (IM
    0.07
     miti
    0.07
    <v
    0.07
     aunt
    0.07
    va
    0.07
     دارای
    0.07
     $('<
    0.07
    Activations Density 0.000%

    No Known Activations