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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 55883
    Prev
    Next
    INDEX
    Explanations

    the

    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
     เพื่อ
    -0.08
     justice
    -0.08
     spotlight
    -0.07
     concer
    -0.07
     noteworthy
    -0.07
     Nested
    -0.07
     incident
    -0.07
     Incident
    -0.07
     subordinate
    -0.07
     निर्देश
    -0.07
    POSITIVE LOGITS
    抵
    0.10
     hostile
    0.08
     pesky
    0.08
    減
    0.08
     steady
    0.08
    Combination
    0.08
    每日
    0.08
    _balance
    0.08
     Combination
    0.08
     detr
    0.08
    Activations Density 0.024%

    No Known Activations