© 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. 94676
    Prev
    Next
    INDEX
    Explanations

    approximately

    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
     terlebih
    -0.08
    あります
    -0.08
     yenye
    -0.08
    ु
    -0.08
     libra
    -0.08
     develops
    -0.07
     muaj
    -0.07
    で
    -0.07
    参
    -0.07
    まず
    -0.07
    POSITIVE LOGITS
    afel
    0.08
     सुझाव
    0.08
     ആശ
    0.08
    正确
    0.08
     वै
    0.07
     hygiene
    0.07
     Hygiene
    0.07
     निष
    0.07
    fr
    0.07
    ğin
    0.07
    Activations Density 0.015%

    No Known Activations