© 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. 30150
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     Sr
    -0.10
     Gara
    -0.10
     الط
    -0.09
     الأط
    -0.09
     للط
    -0.08
    .opacity
    -0.08
     Zoll
    -0.08
     Kara
    -0.08
     المعارضة
    -0.08
     Gaza
    -0.08
    POSITIVE LOGITS
     factorial
    0.10
     adhesive
    0.08
     brute
    0.08
     inad
    0.08
    迁
    0.08
     counts
    0.08
     polynomial
    0.08
    anea
    0.08
     Catal
    0.08
     count
    0.07
    Activations Density 0.011%

    No Known Activations