© 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. 103371
    Prev
    Next
    INDEX
    Explanations

    Korean language

    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
     certain
    -0.10
     bepaalde
    -0.09
     kanilang
    -0.09
    <any
    -0.08
    .")
    -0.08
     tertentu
    -0.08
     forhold
    -0.08
     alcune
    -0.08
     soort
    -0.08
     pagkakata
    -0.08
    POSITIVE LOGITS
    씩
    0.16
     കൂടി
    0.12
    だけ
    0.12
     더
    0.11
    ైనా
    0.10
     mwy
    0.10
    ず
    0.10
    ərbaycan
    0.10
     മാത്രം
    0.09
     подробнее
    0.09
    Activations Density 0.004%

    No Known Activations