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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 52993
    Prev
    Next
    INDEX
    Explanations

    Meeting

    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
    éraux
    -0.08
    در
    -0.08
     vise
    -0.08
     baking
    -0.07
    udar
    -0.07
     LIGHT
    -0.07
     Federação
    -0.07
    bilder
    -0.07
    -0.07
     Byzantine
    -0.07
    POSITIVE LOGITS
     знакомства
    0.12
     знакомств
    0.11
     stumble
    0.10
     başlayan
    0.10
    discover
    0.10
     познаком
    0.10
     incidental
    0.10
     stumbled
    0.09
     kennism
    0.09
    .instant
    0.09
    Activations Density 0.071%

    No Known Activations