© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31557
    Prev
    Next
    INDEX
    Explanations

    日

    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
     vinyl
    -0.08
     nft
    -0.08
    	ans
    -0.08
     NFT
    -0.08
     TVA
    -0.08
     HOA
    -0.08
    ✅
    -0.07
     calibrated
    -0.07
     Tampa
    -0.07
     ozone
    -0.07
    POSITIVE LOGITS
    战争
    0.10
     atrocities
    0.08
     যুদ্ধ
    0.08
    difficulty
    0.08
     వంటి
    0.08
     partida
    0.08
     الحرب
    0.08
     war
    0.08
     युद्ध
    0.08
    侵
    0.08
    Activations Density 0.003%

    No Known Activations