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. 48999
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Vector
    -0.07
    RAW
    -0.07
    .sg
    -0.07
     outcomes
    -0.07
    .Vector
    -0.07
     Outcomes
    -0.07
     workflow
    -0.07
    Workflow
    -0.07
    vector
    -0.07
    _vector
    -0.07
    POSITIVE LOGITS
    启动
    0.11
     listening
    0.10
    .listen
    0.10
    部署
    0.10
     deployments
    0.10
    (PORT
    0.10
     deploying
    0.09
    监听
    0.09
    Listening
    0.09
     Listening
    0.09
    Activations Density 0.005%

    No Known Activations