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. 49320
    Prev
    Next
    INDEX
    Explanations

    .Read

    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
    .bitmap
    -0.09
    efficient
    -0.08
     Habana
    -0.08
     डिजिटल
    -0.08
     digitally
    -0.08
     VIDA
    -0.08
     JO
    -0.08
     thin
    -0.08
     wildfire
    -0.08
     perif
    -0.07
    POSITIVE LOGITS
    ain
    0.09
    entrale
    0.08
     underscores
    0.07
     hinged
    0.07
    ("
    0.07
     gels
    0.07
    敬
    0.07
    ས
    0.07
     র
    0.07
     inför
    0.07
    Activations Density 0.001%

    No Known Activations