© 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 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. 50152
    Prev
    Next
    INDEX
    Explanations

    modular 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
    adece
    -0.09
     mücade
    -0.09
    аличие
    -0.09
     Presence
    -0.08
     наличии
    -0.08
     présence
    -0.08
     иң
    -0.08
    иля
    -0.08
     presence
    -0.08
    Presence
    -0.08
    POSITIVE LOGITS
     wrap
    0.10
    wrap
    0.10
    carry
    0.09
    rotate
    0.09
    (mod
    0.09
    wrapped
    0.09
    ((-
    0.09
    .rotate
    0.09
    .wrap
    0.09
    -wrap
    0.09
    Activations Density 0.052%

    No Known Activations