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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 77431
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    (sockfd
    -0.09
     Belmont
    -0.08
    적인
    -0.08
    .latest
    -0.07
    ੰਜ
    -0.07
    -0.07
    ílio
    -0.07
    .temperature
    -0.07
    (idx
    -0.07
    ેય
    -0.07
    POSITIVE LOGITS
     �
    0.11
     Verd
    0.09
     langue
    0.08
     языке
    0.08
     Sich
    0.08
    中
    0.08
    意思
    0.08
     Scriptures
    0.08
    -speaking
    0.08
     ficar
    0.08
    Activations Density 0.051%

    No Known Activations