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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102862
    Prev
    Next
    INDEX
    Explanations

    health

    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
     dogging
    -0.09
     fiz
    -0.09
    음
    -0.08
     problèmes
    -0.08
     problemática
    -0.08
     fragte
    -0.08
     🙂↵
    -0.08
     фрукт
    -0.08
     koncert
    -0.08
     fruity
    -0.08
    POSITIVE LOGITS
     administration
    0.10
     الخدمة
    0.10
    informatics
    0.10
     Versorgung
    0.10
    -care
    0.10
     delivery
    0.10
    -service
    0.10
     സേവ
    0.10
     సేవ
    0.10
     equity
    0.10
    Activations Density 0.011%

    No Known Activations