© 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. 762
    Prev
    Next
    INDEX
    Explanations

    EM

    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
     Taxi
    -0.08
     brus
    -0.08
    ਸੀ
    -0.08
    ece
    -0.08
     chute
    -0.07
     સે
    -0.07
    burgh
    -0.07
     yas
    -0.07
    Alexander
    -0.07
    chon
    -0.07
    POSITIVE LOGITS
     symptoms
    0.08
     phishing
    0.08
     rewarding
    0.08
    ಂದು
    0.07
     Symptoms
    0.07
     að
    0.07
    เครื่อง
    0.07
     Symptome
    0.07
     reporting
    0.07
     confl
    0.07
    Activations Density 0.002%

    No Known Activations