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. 117708
    Prev
    Next
    INDEX
    Explanations

    sports/soccer

    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
    -0.09
    -custom
    -0.08
     Traits
    -0.08
     polygons
    -0.08
     skul
    -0.08
     ammunition
    -0.08
     compassion
    -0.08
     witnesses
    -0.08
    秘密
    -0.08
     sanding
    -0.08
    POSITIVE LOGITS
    654
    0.08
    sson
    0.08
     객체
    0.08
     재
    0.08
     eryth
    0.08
    国外
    0.08
     국내
    0.08
     obwohl
    0.08
     berger
    0.08
     bài
    0.08
    Activations Density 0.024%

    No Known Activations