© 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. 95015
    Prev
    Next
    INDEX
    Explanations

    reason

    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
    mitted
    -0.08
    -centric
    -0.08
    iens
    -0.08
    pske
    -0.08
    好了
    -0.08
     utensils
    -0.08
    óra
    -0.07
    sw
    -0.07
    cknowled
    -0.07
    CK
    -0.07
    POSITIVE LOGITS
     QModel
    0.10
     Reason
    0.08
     Somehow
    0.08
    ым
    0.08
    .Trigger
    0.08
     norm
    0.08
     inexp
    0.08
    原因
    0.08
     Norm
    0.08
    Reason
    0.08
    Activations Density 0.040%

    No Known Activations