© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129453
    Prev
    Next
    INDEX
    Explanations

    recommendation systems

    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
     prosecute
    -0.09
     prosecut
    -0.09
     prosec
    -0.08
     brace
    -0.08
    、水
    -0.08
     affidavit
    -0.08
     government
    -0.08
     protests
    -0.08
     crane
    -0.08
     prosecution
    -0.07
    POSITIVE LOGITS
     personalization
    0.13
     Personalized
    0.12
     personalized
    0.12
    Caching
    0.11
    猜你喜欢
    0.11
     caching
    0.11
     рейтин
    0.11
     Ratings
    0.11
     用户
    0.11
     playlists
    0.10
    Activations Density 0.020%

    No Known Activations