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. 15-RESID-POST-AA
    6. 19376
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .network
    -0.08
     berasal
    -0.08
     Nectar
    -0.08
    人民日报
    -0.08
     өзі
    -0.08
    .from
    -0.08
    .Horizontal
    -0.08
    uw
    -0.07
    .application
    -0.07
    .pyplot
    -0.07
    POSITIVE LOGITS
     massac
    0.09
     camouflage
    0.09
     arrested
    0.08
    DOWN
    0.08
     abrupt
    0.08
    CACHE
    0.08
     harassment
    0.08
     tactics
    0.08
     shelter
    0.08
    inizi
    0.08
    Activations Density 0.001%

    No Known Activations