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. 88176
    Prev
    Next
    INDEX
    Explanations

    initials

    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
     posing
    -0.08
     insect
    -0.08
    legs
    -0.07
     enthusiasm
    -0.07
     ace
    -0.07
     libros
    -0.07
    .atomic
    -0.07
     besonderes
    -0.07
    <IAction
    -0.07
     आतंक
    -0.07
    POSITIVE LOGITS
     initials
    0.09
    CHE
    0.08
     chapel
    0.08
    ieder
    0.08
     sâu
    0.08
     CHE
    0.07
    ها
    0.07
     avuto
    0.07
     canal
    0.07
     Chambers
    0.07
    Activations Density 0.005%

    No Known Activations