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. 88197
    Prev
    Next
    INDEX
    Explanations

    subtraction and division

    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
    博
    -0.07
    暖
    -0.07
    illors
    -0.07
     lama
    -0.07
     cint
    -0.07
     Kamin
    -0.07
     tav
    -0.07
    听
    -0.07
     berhasil
    -0.07
     iluminação
    -0.07
    POSITIVE LOGITS
    (cancel
    0.09
     subtract
    0.09
    .Cancel
    0.08
     juices
    0.08
    usay
    0.08
     vergel
    0.08
    .subtract
    0.08
    _FORMAT
    0.08
    subtract
    0.08
     ingewikk
    0.08
    Activations Density 0.012%

    No Known Activations