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. 78631
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     الهاتف
    -0.07
     هاتف
    -0.07
    -tv
    -0.07
    -vol
    -0.07
    terror
    -0.07
    .ts
    -0.07
     تس
    -0.07
     hk
    -0.07
    -sem
    -0.07
    ’us
    -0.07
    POSITIVE LOGITS
     Dann
    0.08
    कट
    0.08
    =
    0.07
     reign
    0.07
     swo
    0.07
        			
    0.07
    	ctx
    0.07
    иг
    0.07
    Тол
    0.07
    씩
    0.07
    Activations Density 0.065%

    No Known Activations