© 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. 95312
    Prev
    Next
    INDEX
    Explanations

    |

    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
     embargo
    -0.09
    出版
    -0.08
     Bukkit
    -0.08
    传播
    -0.08
     technologically
    -0.08
     metadata
    -0.08
    通信
    -0.08
    Metadata
    -0.08
     issuance
    -0.08
     conspiracy
    -0.07
    POSITIVE LOGITS
     Pilates
    0.10
     упражнения
    0.10
     repetitions
    0.09
     swim
    0.09
     rowing
    0.09
     Übungen
    0.09
     knie
    0.09
     pelvic
    0.09
    Inspir
    0.09
     swimming
    0.09
    Activations Density 0.009%

    No Known Activations