© 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. 129499
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     flock
    -0.09
     komb
    -0.08
     bro
    -0.08
     vegan
    -0.08
     allerg
    -0.08
     probi
    -0.08
     addictions
    -0.08
     predator
    -0.08
     seminar
    -0.08
     probiotics
    -0.08
    POSITIVE LOGITS
    Tail
    0.09
     Nuit
    0.09
    Digits
    0.09
     deepest
    0.09
     Tail
    0.09
     самые
    0.09
     Highest
    0.09
     Depth
    0.08
     Ebony
    0.08
     contiguous
    0.08
    Activations Density 0.020%

    No Known Activations