© 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. 23-RESID-POST-AA
    11. 48013
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realistic
    -0.11
    environment
    -0.10
     manageable
    -0.10
     mysterious
    -0.10
    SUV
    -0.09
     environment
    -0.09
    BMI
    -0.09
     PTSD
    -0.09
    环境
    -0.09
    HTML
    -0.09
    POSITIVE LOGITS
     eastern
    0.18
     northern
    0.16
     western
    0.16
     southern
    0.15
     Great
    0.15
     east
    0.14
     southeastern
    0.14
     Festival
    0.14
     Eastern
    0.13
     great
    0.13
    Activations Density 0.071%

    No Known Activations