© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69208
    Prev
    Next
    INDEX
    Explanations

    nutrient

    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
     acts
    -0.08
     acting
    -0.08
     troops
    -0.07
     Inspector
    -0.07
     cancel
    -0.07
    NZ
    -0.07
     app
    -0.07
    Inspector
    -0.07
     insider
    -0.07
     BOOL
    -0.07
    POSITIVE LOGITS
     supplementation
    0.09
     충분
    0.09
     ممارسة
    0.08
    Ade
    0.08
    �
    0.08
     китап
    0.08
     vegan
    0.08
     kitap
    0.08
     musul
    0.08
    _span
    0.08
    Activations Density 0.009%

    No Known Activations