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. 88346
    Prev
    Next
    INDEX
    Explanations

    color

    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
     希
    -0.09
    并
    -0.08
     �
    -0.08
     우
    -0.08
     Weighted
    -0.07
     优
    -0.07
    收益
    -0.07
     经纬
    -0.07
    优
    -0.07
    _enable
    -0.07
    POSITIVE LOGITS
     choices
    0.09
    Choices
    0.09
     смен
    0.08
    Restriction
    0.08
     transitions
    0.08
     Choices
    0.08
     differed
    0.08
    .Valid
    0.08
    	options
    0.08
    Avoid
    0.08
    Activations Density 0.012%

    No Known Activations