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. 112109
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     مواقع
    -0.08
     Garg
    -0.08
    ários
    -0.08
     Nearly
    -0.08
     Watkins
    -0.08
     quase
    -0.08
     истин
    -0.07
     criteria
    -0.07
    riteria
    -0.07
     фильма
    -0.07
    POSITIVE LOGITS
     설치
    0.09
    Deprecated
    0.08
    最新版
    0.08
     mannequin
    0.08
     addon
    0.08
    Intl
    0.08
     deprecated
    0.08
    deprecated
    0.08
     instalación
    0.08
     actuator
    0.08
    Activations Density 0.015%

    No Known Activations