© 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. 63881
    Prev
    Next
    INDEX
    Explanations

    quant

    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
     Hex
    -0.09
     Afternoon
    -0.08
    Taxes
    -0.08
    Exterior
    -0.08
    Categorie
    -0.08
    一家
    -0.08
     subcontract
    -0.08
     Oyster
    -0.08
    _sink
    -0.08
    Ownership
    -0.08
    POSITIVE LOGITS
     标
    0.10
     scipy
    0.10
    標
    0.09
     percentile
    0.09
    标
    0.09
    密码
    0.09
     calibration
    0.09
     գործ
    0.08
    (log
    0.08
    标准
    0.08
    Activations Density 0.008%

    No Known Activations