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. 56236
    Prev
    Next
    INDEX
    Explanations

    points

    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
    iah
    -0.08
     keyword
    -0.08
    ==
    -0.08
    alah
    -0.08
     Fo
    -0.07
    投
    -0.07
    决定
    -0.07
     impetus
    -0.07
     hydro
    -0.07
     SG
    -0.07
    POSITIVE LOGITS
    stones
    0.10
    imals
    0.09
     राजा
    0.08
    .vertices
    0.08
    hawks
    0.08
     चिक
    0.08
     भेट
    0.08
     alojamiento
    0.08
    _CONNECTED
    0.08
     polygons
    0.08
    Activations Density 0.007%

    No Known Activations