© 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. 94915
    Prev
    Next
    INDEX
    Explanations

    local economy, money

    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
    �
    -0.09
     Manage
    -0.08
    Full
    -0.08
     Full
    -0.08
    .Full
    -0.08
    full
    -0.07
     FULL
    -0.07
    שם
    -0.07
    כם
    -0.07
    .PERMISSION
    -0.07
    POSITIVE LOGITS
     redistributed
    0.13
     redistribute
    0.11
     redistribution
    0.11
     distributes
    0.11
     Redistribution
    0.10
     distribute
    0.09
     денег
    0.09
     wirkt
    0.09
     répart
    0.09
     distribuir
    0.09
    Activations Density 0.012%

    No Known Activations