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. 119721
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
     unix
    -0.08
    .Password
    -0.08
     [+
    -0.08
     UTC
    -0.07
    ajā
    -0.07
     неск
    -0.07
     insecure
    -0.07
    .literal
    -0.07
    geladen
    -0.07
    fld
    -0.07
    POSITIVE LOGITS
     decomposition
    0.09
     Scam
    0.08
     ite
    0.08
     triang
    0.08
     Sewing
    0.08
     coastline
    0.08
     Sweep
    0.08
     polygon
    0.08
     segmentation
    0.08
    Connectivity
    0.08
    Activations Density 0.019%

    No Known Activations