© 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. 103635
    Prev
    Next
    INDEX
    Explanations

    name

    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
    Commentaires
    -0.08
    コメント
    -0.08
     댓글
    -0.08
    acomment
    -0.08
     टिप्प
    -0.08
     মন্তব্য
    -0.08
     commentaires
    -0.08
     hypot
    -0.08
    -comments
    -0.08
    رز
    -0.08
    POSITIVE LOGITS
     name
    0.12
    ,name
    0.12
    .name
    0.11
    	name
    0.11
    name
    0.10
    (name
    0.10
     이름
    0.10
     species
    0.10
    =name
    0.10
     имя
    0.10
    Activations Density 0.003%

    No Known Activations