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. 58788
    Prev
    Next
    INDEX
    Explanations

    for

    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
     ಮಾನ
    -0.08
     enforced
    -0.08
    inum
    -0.08
    -0.07
    lement
    -0.07
     consiste
    -0.07
     πα
    -0.07
     provis
    -0.07
    Prescription
    -0.07
    ecta
    -0.07
    POSITIVE LOGITS
    キャン
    0.09
     purposes
    0.09
    助手
    0.09
    一家
    0.08
    课堂
    0.08
    gatsby
    0.08
     aspiring
    0.08
    具
    0.08
     osoby
    0.08
     diary
    0.08
    Activations Density 0.026%

    No Known Activations