Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 52997
    Prev
    Next
    INDEX
    Explanations

    Java code and tests

    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
     št
    -0.09
     towing
    -0.08
    _four
    -0.08
    wort
    -0.08
    bereitung
    -0.08
    vellous
    -0.08
    _tri
    -0.08
     investieren
    -0.08
    Fern
    -0.08
    _vertex
    -0.08
    POSITIVE LOGITS
     Exception
    0.08
    Exception
    0.07
    0.07
    .expect
    0.07
    .Promise
    0.07
    .assert
    0.07
    .Permission
    0.07
     צר
    0.07
    ouw
    0.07
    期期
    0.07
    Activations Density 0.001%

    No Known Activations