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

    Neuronpedia

    APICircuit 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. 58628
    Prev
    Next
    INDEX
    Explanations

    What

    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
    ::~
    -0.09
    Bounding
    -0.08
    .font
    -0.07
     클래
    -0.07
     riots
    -0.07
     들
    -0.07
     linestyle
    -0.07
     bordered
    -0.07
    td
    -0.07
    bounding
    -0.07
    POSITIVE LOGITS
     WHAT
    0.09
     talk
    0.08
     משהו
    0.08
     aquilo
    0.08
     ומה
    0.08
     چیزی
    0.08
     қалай
    0.08
     concr
    0.08
    ,包括
    0.08
    How
    0.08
    Activations Density 0.051%

    No Known Activations