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. 75951
    Prev
    Next
    INDEX
    Explanations

    ing

    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
     seamlessly
    -0.08
    prite
    -0.08
    .cod
    -0.07
     seamless
    -0.07
     Daf
    -0.07
    mooth
    -0.07
    орус
    -0.07
    pring
    -0.07
     Oll
    -0.07
    pert
    -0.07
    POSITIVE LOGITS
     exhilar
    0.10
    喘
    0.09
     thrills
    0.09
     proč
    0.08
     horsepower
    0.08
     fumes
    0.08
     brake
    0.08
    原因
    0.08
    856
    0.07
     GTX
    0.07
    Activations Density 0.005%

    No Known Activations