© 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. 47841
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    دخل
    -0.09
     convicted
    -0.09
     населения
    -0.09
    က္
    -0.09
     censorship
    -0.09
     науки
    -0.09
    Doctors
    -0.09
    -polit
    -0.09
     заболев
    -0.08
     insults
    -0.08
    POSITIVE LOGITS
    型号
    0.16
     Series
    0.11
    シリーズ
    0.11
    系列
    0.10
    ®
    0.10
     chassis
    0.10
    360
    0.10
     piston
    0.10
    ™
    0.10
     รุ่น
    0.09
    Activations Density 0.132%

    No Known Activations