© 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. 78875
    Prev
    Next
    INDEX
    Explanations

    decomposition

    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
     cardinal
    -0.09
     Pricing
    -0.08
     Cardinal
    -0.08
     Fish
    -0.07
     администра
    -0.07
     pricing
    -0.07
     Mauro
    -0.07
    ицин
    -0.07
     sortie
    -0.07
     princip
    -0.07
    POSITIVE LOGITS
    掉
    0.08
     mildew
    0.08
     langsam
    0.08
     nhanh
    0.08
    过程中
    0.08
    老
    0.08
     પ્રક્ર
    0.08
    covered
    0.08
     biodegradable
    0.08
     الطبيعية
    0.07
    Activations Density 0.011%

    No Known Activations