© 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. 102
    Prev
    Next
    INDEX
    Explanations

    artist

    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
    аша
    -0.08
     muscular
    -0.08
    కు
    -0.08
    артф
    -0.07
     elimin
    -0.07
     Elimin
    -0.07
     уб
    -0.07
     з
    -0.07
    亚
    -0.07
     Bruno
    -0.07
    POSITIVE LOGITS
     sui
    0.07
    কল
    0.07
     inclined
    0.07
     flour
    0.07
    inp
    0.07
    貌
    0.07
     dias
    0.07
     peint
    0.07
     cand
    0.07
     मालिक
    0.07
    Activations Density 0.039%

    No Known Activations