© 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. 112412
    Prev
    Next
    INDEX
    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
    北京时间
    -0.09
     Barack
    -0.09
     Congressional
    -0.08
     aad
    -0.08
     Arabia
    -0.08
    官方下载
    -0.08
    追回
    -0.08
    BITS
    -0.08
    baz
    -0.08
     Brace
    -0.08
    POSITIVE LOGITS
    运营
    0.12
    スタッフ
    0.12
    营销
    0.11
    装修
    0.11
     merchandising
    0.11
     profitability
    0.11
     marketing
    0.11
    经营
    0.11
     renovation
    0.11
     অতিথ
    0.11
    Activations Density 0.066%

    No Known Activations