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. 53967
    Prev
    Next
    INDEX
    Explanations

    Easements

    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
     сертифик
    -0.09
     retry
    -0.09
    _retry
    -0.09
     한번
    -0.09
     리뷰
    -0.08
     расслед
    -0.08
     окно
    -0.08
     Malware
    -0.08
     triunfo
    -0.08
    Retry
    -0.08
    POSITIVE LOGITS
     neighboring
    0.09
     leased
    0.09
    �
    0.08
    地下
    0.08
    土地
    0.08
     usuf
    0.08
    Subdivision
    0.08
    設備
    0.08
     factions
    0.08
    ipel
    0.08
    Activations Density 0.023%

    No Known Activations