© 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. 68229
    Prev
    Next
    INDEX
    Explanations

    pressure

    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
     pilgr
    -0.09
     چون
    -0.08
     이후
    -0.08
     archaeology
    -0.08
    _TOP
    -0.08
     제외
    -0.07
    Excluded
    -0.07
     erscheinen
    -0.07
     pilgrims
    -0.07
     одежды
    -0.07
    POSITIVE LOGITS
    健康
    0.08
     monitoring
    0.08
     khỏe
    0.08
    alg
    0.07
     unpaid
    0.07
    纹
    0.07
     health
    0.07
     santé
    0.07
     Health
    0.07
    监
    0.07
    Activations Density 0.005%

    No Known Activations