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. 12920
    Prev
    Next
    INDEX
    Explanations

    durable

    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
     dérou
    -0.09
    Elementary
    -0.08
     Elementary
    -0.08
     दिश
    -0.08
     fai
    -0.07
     వచ్చిన
    -0.07
     axi
    -0.07
     Normal
    -0.07
     elementary
    -0.07
     unwind
    -0.07
    POSITIVE LOGITS
    pic
    0.08
    良
    0.08
     plaques
    0.07
     constit
    0.07
    Pl
    0.07
    환경
    0.07
    goods
    0.07
    જે
    0.07
    en
    0.07
    /Re
    0.07
    Activations Density 0.008%

    No Known Activations