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. 27319
    Prev
    Next
    INDEX
    Explanations

    agar, gel, 脂

    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
     multif
    -0.08
     Multif
    -0.08
    -performance
    -0.08
     Imported
    -0.08
     showcased
    -0.08
     lợi
    -0.07
    ztat
    -0.07
     htmlentities
    -0.07
    Antonio
    -0.07
     gün
    -0.07
    POSITIVE LOGITS
     तयार
    0.09
     medium
    0.08
     slurry
    0.08
     બનાવી
    0.08
     FG
    0.07
     Burke
    0.07
     chemically
    0.07
     leid
    0.07
     മാധ്യമ
    0.07
     pellets
    0.07
    Activations Density 0.003%

    No Known Activations