© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47472
    Prev
    Next
    INDEX
    Explanations

    ```

    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
    .↵↵//
    -0.11
    Uint
    -0.10
    ')↵↵//
    -0.10
    .liferay
    -0.10
    ");↵↵//
    -0.10
    "↵↵//
    -0.09
    .
↵//
↵//
    -0.09
    $stmt
    -0.09
    .scss
    -0.09
    @Json
    -0.09
    POSITIVE LOGITS
    python
    0.39
     python
    0.35
     Python
    0.32
    Python
    0.30
    _python
    0.25
    /python
    0.24
    .python
    0.24
    -python
    0.22
    py
    0.21
     py
    0.20
    Activations Density 0.006%

    No Known Activations