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. 30123
    Prev
    Next
    INDEX
    Explanations

    recommendations

    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
     procès
    -0.11
    vrt
    -0.09
    елич
    -0.09
    irdi
    -0.08
    oplast
    -0.08
    operand
    -0.08
     apariencia
    -0.08
    hapus
    -0.08
     Asamblea
    -0.08
    нення
    -0.08
    POSITIVE LOGITS
    推荐
    0.18
     추천
    0.18
     recommendations
    0.16
     recommendation
    0.15
     Empfehlungen
    0.15
     推荐
    0.15
     Recommendations
    0.15
     recommending
    0.15
    推薦
    0.15
     Recommendation
    0.14
    Activations Density 0.070%

    No Known Activations