© 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. 11-RESID-POST-AA
    11. 69596
    Prev
    Next
    INDEX
    Explanations

    math problem explanations

    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
    Tl
    -0.08
     gearing
    -0.08
    納
    -0.07
     použ
    -0.07
    纳
    -0.07
    此同时
    -0.07
    unningham
    -0.07
     nab
    -0.07
    endoza
    -0.07
    ாது
    -0.07
    POSITIVE LOGITS
    amount
    0.08
    .count
    0.08
     figur
    0.07
     percent
    0.07
    Hall
    0.07
     portions
    0.07
    incident
    0.07
    .bus
    0.07
     amount
    0.07
     сумму
    0.07
    Activations Density 0.126%

    No Known Activations