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. 88150
    Prev
    Next
    INDEX
    Explanations

    son

    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
    -0.08
     Disse
    -0.08
    veyor
    -0.07
     lad
    -0.07
    撒
    -0.07
     Recommendation
    -0.07
    ste
    -0.07
    惠
    -0.07
     Lad
    -0.07
    907
    -0.07
    POSITIVE LOGITS
     unhappy
    0.09
     desagrad
    0.08
    �்கள்
    0.08
     cac
    0.08
     uneasy
    0.08
     Peaks
    0.08
     সৃষ্টি
    0.08
     unpleasant
    0.08
     хор
    0.08
     विरोध
    0.08
    Activations Density 0.002%

    No Known Activations