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. 59462
    Prev
    Next
    INDEX
    Explanations

    project scaffolding

    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
     Earth's
    -0.09
     חי
    -0.08
     transmit
    -0.08
    运输
    -0.08
     transmitir
    -0.08
     Sabbath
    -0.08
    臣
    -0.08
     хит
    -0.08
     Bandar
    -0.08
    投诉
    -0.08
    POSITIVE LOGITS
     Starter
    0.13
    (template
    0.13
    Template
    0.13
     starter
    0.13
    _template
    0.12
     scaff
    0.12
    .Template
    0.12
    模板
    0.12
    Starter
    0.12
    template
    0.12
    Activations Density 0.025%

    No Known Activations