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. 42324
    Prev
    Next
    INDEX
    Explanations

    quotes and conversational

    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
    (wrapper
    -0.08
    Issued
    -0.08
    SHA
    -0.08
     kand
    -0.08
     chiqar
    -0.08
    াঙ্গ
    -0.07
     शरी
    -0.07
     rū
    -0.07
    _si
    -0.07
     mhaith
    -0.07
    POSITIVE LOGITS
     Primitive
    0.08
     Hockey
    0.08
     Appalachian
    0.08
     Nordic
    0.08
     primitive
    0.08
    Primitive
    0.07
     Milo
    0.07
     Hardcore
    0.07
     Hairst
    0.07
     dod
    0.07
    Activations Density 0.001%

    No Known Activations