© 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. 108613
    Prev
    Next
    INDEX
    Explanations

    ray-tracing

    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
     Soci
    -0.09
    Prefab
    -0.09
     Hatch
    -0.08
    ære
    -0.07
     ethn
    -0.07
    การณ์
    -0.07
     Ger
    -0.07
     know
    -0.07
    다면
    -0.07
     Kann
    -0.07
    POSITIVE LOGITS
     slows
    0.09
     engages
    0.08
    -enabled
    0.08
     Heavy
    0.08
    Heavy
    0.08
    -heavy
    0.08
     bater
    0.08
     einzel
    0.08
    mazing
    0.08
     einzelne
    0.08
    Activations Density 0.001%

    No Known Activations