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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18981
    Prev
    Next
    INDEX
    Explanations

    Also

    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
     (
    -0.10
     Starts
    -0.10
     一号
    -0.09
    Starts
    -0.09
    (...)↵
    -0.09
     (**
    -0.09
     或
    -0.09
     Initializes
    -0.09
     또는
    -0.09
     Bahkan
    -0.09
    POSITIVE LOGITS
     consider
    0.19
     ensure
    0.18
     incorporate
    0.18
     remember
    0.17
     include
    0.16
     berücksicht
    0.16
     note
    0.16
    考虑
    0.16
     use
    0.15
     disclaim
    0.15
    Activations Density 0.054%

    No Known Activations