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. 106162
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Brows
    -0.10
    用
    -0.09
    努力
    -0.09
    ※
    -0.09
    сем
    -0.09
    .е
    -0.09
    ดับ
    -0.08
    ご
    -0.08
    үүд
    -0.08
    ੱਸ
    -0.08
    POSITIVE LOGITS
     शिक
    0.08
     Pose
    0.08
    กระ
    0.08
     analogy
    0.07
     morg
    0.07
     Puebla
    0.07
    RU
    0.07
     Increasing
    0.07
     Reforma
    0.07
    abil
    0.07
    Activations Density 0.002%

    No Known Activations