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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103441
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ودة
    -0.08
     два
    -0.08
    ительство
    -0.08
     Friedman
    -0.08
     দিলে
    -0.08
     потому
    -0.08
    (Tab
    -0.08
    (router
    -0.08
    (Search
    -0.08
    (Vue
    -0.08
    POSITIVE LOGITS
    ’s
    0.12
    's
    0.11
     video's
    0.10
     item's
    0.09
     game's
    0.09
    ‘s
    0.09
     application's
    0.09
     摄
    0.09
    çinin
    0.09
    ."),↵
    0.09
    Activations Density 0.002%

    No Known Activations