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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48067
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Veuillez
    -0.09
     hoping
    -0.09
    様
    -0.08
     برخی
    -0.08
    をご
    -0.08
     જોવા
    -0.08
    den
    -0.08
     باغ
    -0.08
    期待
    -0.08
     willingly
    -0.08
    POSITIVE LOGITS
     구현
    0.11
     Dispatcher
    0.09
     APIs
    0.09
    实现
    0.09
     algorithms
    0.09
     Algorithm
    0.09
     реализ
    0.09
     storing
    0.09
     отображ
    0.09
    Dispatcher
    0.09
    Activations Density 0.061%

    No Known Activations