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. 43750
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     grids
    -0.09
    塑
    -0.08
     feu
    -0.08
    ำน
    -0.08
    揭
    -0.08
     aufreg
    -0.08
     altında
    -0.07
    iyy
    -0.07
    زز
    -0.07
    ]}"
    -0.07
    POSITIVE LOGITS
    /example
    0.08
     regio
    0.08
    pane
    0.08
     regi
    0.07
     halves
    0.07
    .Editor
    0.07
    zburg
    0.07
     prve
    0.07
    on
    0.07
     hom
    0.07
    Activations Density 0.007%

    No Known Activations