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. 43336
    Prev
    Next
    INDEX
    Explanations

    baseball players

    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
    .PL
    -0.08
     establishes
    -0.08
     alent
    -0.07
     establishment
    -0.07
    .SP
    -0.07
     полно
    -0.07
     Bann
    -0.07
    .syn
    -0.07
    .sp
    -0.07
     Largo
    -0.07
    POSITIVE LOGITS
    utrients
    0.08
    加盟
    0.08
     trusty
    0.08
     mysl
    0.08
    心
    0.08
     selfish
    0.08
    rhs
    0.07
    0.07
     tired
    0.07
    œurs
    0.07
    Activations Density 0.050%

    No Known Activations