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. 53951
    Prev
    Next
    INDEX
    Explanations

    protective films and seals

    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
    派
    -0.08
    gres
    -0.08
    terra
    -0.08
     ethnicity
    -0.08
    讯网
    -0.08
     county
    -0.08
    èles
    -0.08
     Oct
    -0.08
     Beled
    -0.08
     Metals
    -0.08
    POSITIVE LOGITS
     unopened
    0.08
     und
    0.08
     box
    0.07
    oods
    0.07
     nipples
    0.07
    _nd
    0.07
    _box
    0.07
    包装
    0.07
    -box
    0.07
     discharged
    0.07
    Activations Density 0.029%

    No Known Activations