© 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. 108773
    Prev
    Next
    INDEX
    Explanations

    the, of

    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
     experimenting
    -0.08
    ffected
    -0.08
    iect
    -0.08
     imaginable
    -0.08
    ਨਾਂ
    -0.08
    ਤੀ
    -0.08
    考试
    -0.07
    且
    -0.07
    娱乐
    -0.07
     speculate
    -0.07
    POSITIVE LOGITS
     он
    0.08
     hermanos
    0.07
     Indianapolis
    0.07
     này
    0.07
     lõ
    0.07
     backpacks
    0.07
     передач
    0.07
     Least
    0.07
     dây
    0.07
     diket
    0.07
    Activations Density 0.056%

    No Known Activations