© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 600
    Prev
    Next
    INDEX
    Explanations

    **

    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
    Lifetime
    -0.08
    年份
    -0.08
     offert
    -0.07
     tunnels
    -0.07
     biy
    -0.07
    asto
    -0.07
     financially
    -0.07
    toon
    -0.07
     dham
    -0.07
    ittäin
    -0.07
    POSITIVE LOGITS
     consultant
    0.08
     Consultant
    0.08
     Sofia
    0.08
     Jess
    0.08
     Él
    0.08
     Actress
    0.07
     Buddy
    0.07
     Satan
    0.07
     rotating
    0.07
     furious
    0.07
    Activations Density 0.005%

    No Known Activations