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. 58155
    Prev
    Next
    INDEX
    Explanations

    equation simplification by cancelling

    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
     осво
    -0.09
     Corpor
    -0.08
     calculated
    -0.08
     કોર્�
    -0.08
     corporations
    -0.08
     energet
    -0.08
     beantworten
    -0.08
    stacle
    -0.08
     Warm
    -0.07
     пока
    -0.07
    POSITIVE LOGITS
     mour
    0.08
    ୍
    0.08
    لغاء
    0.08
    �
    0.07
    旗下
    0.07
     Cancel
    0.07
    Cancel
    0.07
     kabi
    0.07
    (cancel
    0.07
     redundant
    0.07
    Activations Density 0.046%

    No Known Activations