Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12674
    Prev
    Next
    INDEX
    Explanations

    financial and legal planning

    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
     heuristic
    -0.07
     engaged
    -0.07
    Dell
    -0.07
     mism
    -0.07
     Helm
    -0.07
     sleeping
    -0.07
     desconhe
    -0.07
     desconoc
    -0.07
     polymers
    -0.07
     deber
    -0.07
    POSITIVE LOGITS
     करव
    0.09
    앙
    0.08
    �
    0.08
     ವಾಹ
    0.08
     للأطفال
    0.08
    ಕರಣ
    0.08
     ಉತ್ತಮ
    0.08
     ಹಣ
    0.08
    >()↵
    0.08
     bankruptcy
    0.08
    Activations Density 0.009%

    No Known Activations