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. 120393
    Prev
    Next
    INDEX
    Explanations

    sequential actions

    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
    送
    -0.08
    ardon
    -0.07
    ази
    -0.07
    伯
    -0.07
     fertile
    -0.07
     ctor
    -0.07
    궁
    -0.07
     genial
    -0.07
     �
    -0.07
     urged
    -0.07
    POSITIVE LOGITS
     sequential
    0.14
     Sequential
    0.13
    Sequential
    0.13
    .Sequential
    0.09
     stagger
    0.09
     Vorr
    0.09
    /sw
    0.09
     vone
    0.08
     successive
    0.08
     interchangeable
    0.08
    Activations Density 0.023%

    No Known Activations