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. 53407
    Prev
    Next
    INDEX
    Explanations

    Relationships

    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
     полной
    -0.08
     труд
    -0.08
     polyval
    -0.08
    Grinding
    -0.08
    pske
    -0.08
     survived
    -0.08
     ನೀಡಿದ್ದಾರೆ
    -0.07
    verb
    -0.07
    ervolle
    -0.07
     vermitt
    -0.07
    POSITIVE LOGITS
    として
    0.10
     হিসেবে
    0.08
    就是
    0.08
     namely
    0.08
     म्हणून
    0.08
     તરીકે
    0.07
     olan
    0.07
    是谁
    0.07
     aka
    0.07
     হিসাবে
    0.07
    Activations Density 0.139%

    No Known Activations