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. 58849
    Prev
    Next
    INDEX
    Explanations

    apikey

    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
     논
    -0.10
    論
    -0.09
    논
    -0.07
    aston
    -0.07
     Historically
    -0.07
    로
    -0.07
     "','
    -0.07
    를
    -0.07
     Britain
    -0.07
    asion
    -0.07
    POSITIVE LOGITS
    Balancer
    0.08
    0.08
    攻略
    0.08
     ratka
    0.07
     pensée
    0.07
     नाव
    0.07
     वर
    0.07
    BAL
    0.07
    122
    0.07
    డం
    0.07
    Activations Density 0.000%

    No Known Activations