Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120134
    Prev
    Next
    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gärna
    -0.10
     graag
    -0.09
    出了
    -0.08
     मग
    -0.08
     Schol
    -0.08
     gotta
    -0.08
    łącz
    -0.08
     duh
    -0.08
     XIV
    -0.08
     Defines
    -0.08
    POSITIVE LOGITS
     dependendo
    0.14
     dependiendo
    0.13
     depending
    0.13
    depending
    0.10
     Depending
    0.10
    Depending
    0.09
     someday
    0.09
     afhankelijk
    0.09
     ٿي
    0.09
    ਦੀ
    0.08
    Activations Density 0.557%

    No Known Activations