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. 77379
    Prev
    Next
    INDEX
    Explanations

    Math expressions

    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
     paranormal
    -0.07
     Victorian
    -0.07
     apostas
    -0.07
    َّه
    -0.07
     Venda
    -0.07
     patrones
    -0.07
     Access
    -0.07
     conten
    -0.07
     Media
    -0.07
     Par
    -0.07
    POSITIVE LOGITS
     dictate
    0.09
    Reached
    0.09
     czerw
    0.09
     inset
    0.08
    .xy
    0.08
     CGPoint
    0.08
    Mak
    0.08
    bogen
    0.08
    _xlim
    0.08
     jun
    0.08
    Activations Density 0.021%

    No Known Activations