© 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. 102919
    Prev
    Next
    INDEX
    Explanations

    say "+" symbol

    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
     depreci
    -0.09
     Comparing
    -0.08
     Comparator
    -0.08
     occurring
    -0.08
     compared
    -0.08
     comparable
    -0.08
     ministerie
    -0.08
     Tram
    -0.08
    ۱۳
    -0.08
     følgende
    -0.08
    POSITIVE LOGITS
    +i
    0.09
     +
    0.08
    ,
    0.08
    ਸ
    0.08
    swift
    0.07
    inos
    0.07
     Adam
    0.07
     애
    0.07
    -i
    0.07
    ,time
    0.07
    Activations Density 0.004%

    No Known Activations