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. 11857
    Prev
    Next
    INDEX
    Explanations

    the

    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
     proactive
    -0.08
     increments
    -0.08
     divisible
    -0.08
     trải
    -0.08
     bà
    -0.08
    -Be
    -0.08
     ожид
    -0.08
    ="""
    -0.07
     Experiences
    -0.07
     heißen
    -0.07
    POSITIVE LOGITS
    Scope
    0.08
    alb
    0.08
    EU
    0.07
    Hem
    0.07
    ML
    0.07
    REE
    0.07
     চ
    0.07
    In
    0.07
     scope
    0.07
    cart
    0.07
    Activations Density 0.002%

    No Known Activations