© 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. 23-RESID-POST-AA
    11. 47548
    Prev
    Next
    INDEX
    Explanations

    活

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     komu
    -0.09
    ಮು
    -0.08
     尚
    -0.08
     prava
    -0.08
     vertra
    -0.08
     urrainn
    -0.08
     unir
    -0.08
     tahu
    -0.07
     mangrupikeun
    -0.07
     mengen
    -0.07
    POSITIVE LOGITS
    跃
    0.21
    力
    0.14
    �
    0.14
    �
    0.12
    络
    0.12
    塞
    0.12
    력
    0.11
    絡
    0.11
    력을
    0.11
    력이
    0.10
    Activations Density 0.002%

    No Known Activations