© 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. 68312
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     Start
    -0.08
    ,start
    -0.08
    ,address
    -0.08
     startups
    -0.07
     ungef
    -0.07
     friend
    -0.07
     manque
    -0.07
     класса
    -0.07
     экземпля
    -0.07
     Smart
    -0.07
    POSITIVE LOGITS
     influences
    0.14
     influência
    0.11
     influenced
    0.11
     beïnv
    0.11
    Influ
    0.10
     영향을
    0.10
     contributions
    0.10
     influence
    0.10
     origins
    0.10
     influ
    0.10
    Activations Density 0.029%

    No Known Activations