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. 49184
    Prev
    Next
    INDEX
    Explanations

    articulate

    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
     Bag
    -0.07
     Bala
    -0.07
     hai
    -0.07
     fat
    -0.07
    leiter
    -0.07
    Bag
    -0.07
     Sala
    -0.07
     qua
    -0.07
     bag
    -0.07
     Tout
    -0.07
    POSITIVE LOGITS
     clairement
    0.09
     claramente
    0.09
     clearly
    0.08
     verbal
    0.08
     articulate
    0.08
     இருக்க
    0.07
    为何
    0.07
    tent
    0.07
    MENT
    0.07
     grievances
    0.07
    Activations Density 0.003%

    No Known Activations