Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 60768
    Prev
    Next
    INDEX
    Explanations

    about

    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
     বাস
    -0.08
     Astr
    -0.08
     }↵//
    -0.08
    ম
    -0.07
     similarly
    -0.07
     trunk
    -0.07
     palm
    -0.07
     ভার
    -0.07
     Pants
    -0.07
     Canal
    -0.07
    POSITIVE LOGITS
     aided
    0.09
    леж
    0.09
     hiervoor
    0.09
     ამის
    0.08
     ამას
    0.08
     endeavors
    0.08
    -span
    0.08
     müdd
    0.08
     ნებისმიერი
    0.08
     endeavor
    0.07
    Activations Density 0.021%

    No Known Activations