© 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. 3-RESID-POST-AA
    11. 2713
    Prev
    Next
    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poj
    -0.08
     Stella
    -0.08
     Patr
    -0.08
     Opera
    -0.08
    atrice
    -0.07
     spro
    -0.07
     등장
    -0.07
    录
    -0.07
     inco
    -0.07
    וסר
    -0.07
    POSITIVE LOGITS
     perfe
    0.07
     ami
    0.07
    elect
    0.07
     Xe
    0.07
     له
    0.07
     çalışmalar
    0.07
    ести
    0.07
    ستی
    0.07
    گر
    0.07
     uuring
    0.07
    Activations Density 0.003%

    No Known Activations