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. 77330
    Prev
    Next
    INDEX
    Explanations

    glance

    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
    anim
    -0.07
     audition
    -0.07
     Experiences
    -0.07
     Springs
    -0.07
    anical
    -0.07
    -0.07
     termites
    -0.07
    നും
    -0.07
    EINVAL
    -0.07
    tf
    -0.07
    POSITIVE LOGITS
     glance
    0.09
    速
    0.08
     departed
    0.08
     clin
    0.08
     жасап
    0.08
    abase
    0.08
     shoulders
    0.08
     cht
    0.08
     glanced
    0.07
     Jordan
    0.07
    Activations Density 0.003%

    No Known Activations