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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6248
    Prev
    Next
    INDEX
    Explanations

    modulo arithmetic

    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
    %'↵
    -0.12
    %"↵
    -0.11
    %',
    -0.11
    %',↵
    -0.10
    %'
    -0.10
    %"
    -0.10
    ％
    -0.10
    %的
    -0.10
    %,
    -0.10
    /%
    -0.10
    POSITIVE LOGITS
     ẹ
    0.09
     werd
    0.09
     ubut
    0.08
     embod
    0.08
     Rua
    0.08
     ịch
    0.08
     ocurrió
    0.08
    되고
    0.08
     ocorreu
    0.08
     ake
    0.08
    Activations Density 0.015%

    No Known Activations