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. 106226
    Prev
    Next
    INDEX
    Explanations

    electrical circuits

    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
     sturdy
    -0.09
    Slug
    -0.09
    Singleton
    -0.08
    itorial
    -0.08
     Luxemb
    -0.08
    _slug
    -0.08
    徴
    -0.08
     backpack
    -0.08
    -copy
    -0.08
     Lein
    -0.08
    POSITIVE LOGITS
     delay
    0.10
     Voc
    0.10
    delay
    0.10
     eléctricos
    0.09
     atraso
    0.09
     radians
    0.09
    同期
    0.09
     sähkö
    0.09
     oras
    0.09
     shift
    0.09
    Activations Density 0.005%

    No Known Activations