© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1450
    Prev
    Next
    INDEX
    Explanations

    ```

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tolerate
    -0.09
     favourable
    -0.08
    ebr
    -0.07
    پ
    -0.07
    quiet
    -0.07
     hybrid
    -0.07
    lear
    -0.07
     movement
    -0.07
     namespaces
    -0.07
     fec
    -0.07
    POSITIVE LOGITS
     forge
    0.08
    (param
    0.07
     Cho
    0.07
     Ole
    0.07
     leveraged
    0.07
     patriot
    0.07
     kompleks
    0.07
    332
    0.07
    毕
    0.07
    &T
    0.07
    Activations Density 0.001%

    No Known Activations