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. 77340
    Prev
    Next
    INDEX
    Explanations

    debugging

    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
     hostess
    -0.08
     propon
    -0.08
     predator
    -0.08
     runway
    -0.08
     kag
    -0.08
    Offering
    -0.07
    Approve
    -0.07
     sensual
    -0.07
    .offer
    -0.07
     komis
    -0.07
    POSITIVE LOGITS
    _symbols
    0.08
    symbols
    0.08
     legitimate
    0.08
     intros
    0.08
     pdb
    0.08
     Symbols
    0.07
     perdida
    0.07
    -paid
    0.07
     libc
    0.07
     detectable
    0.07
    Activations Density 0.003%

    No Known Activations