© 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. 54920
    Prev
    Next
    INDEX
    Explanations

    Augustus

    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
     gehad
    -0.09
    交換
    -0.09
    raska
    -0.09
     Swap
    -0.08
     داریم
    -0.08
    DAR
    -0.08
     кызы
    -0.08
    TOD
    -0.08
    Danger
    -0.08
    もっと
    -0.08
    POSITIVE LOGITS
     définitivement
    0.09
     consolidation
    0.09
    建立
    0.09
     victory
    0.09
    ecure
    0.08
     establishment
    0.08
     settle
    0.08
     dynasty
    0.08
     settles
    0.08
     victorious
    0.08
    Activations Density 0.010%

    No Known Activations