© 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. 102291
    Prev
    Next
    INDEX
    Explanations

    say des

    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
     kët
    -0.11
     þessu
    -0.11
     této
    -0.10
     гэтай
    -0.10
    ไหนดี
    -0.10
    รั่ง
    -0.09
    รั่งเศ
    -0.09
    ังค
    -0.09
     нему
    -0.09
     tähän
    -0.09
    POSITIVE LOGITS
     các
    0.19
     les
    0.16
    的
    0.16
     des
    0.15
     of
    0.14
    's
    0.14
     delle
    0.14
     mga
    0.13
     τις
    0.13
     awọn
    0.13
    Activations Density 0.024%

    No Known Activations