© 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. 45375
    Prev
    Next
    INDEX
    Explanations

    lost

    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
    adj
    -0.08
    ್ಷ
    -0.08
    ό
    -0.08
     ich
    -0.07
     clips
    -0.07
    .platform
    -0.07
    261
    -0.07
    hm
    -0.07
     Secretary
    -0.07
     jab
    -0.07
    POSITIVE LOGITS
     wandering
    0.10
     ਜਾਣ
    0.09
     потер
    0.08
     Blo
    0.08
     hopeless
    0.08
    迷
    0.08
     counsel
    0.08
    導航
    0.08
     Nemo
    0.08
     struggle
    0.08
    Activations Density 0.015%

    No Known Activations