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. 55457
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    stackoverflow
    -0.08
     soy
    -0.08
     copp
    -0.07
    clas
    -0.07
     cloth
    -0.07
    ಿತ್ತು
    -0.07
    Semaphore
    -0.07
     bathing
    -0.07
    orian
    -0.07
     Cloth
    -0.07
    POSITIVE LOGITS
    겁
    0.08
     decidedly
    0.08
     വിവ
    0.08
    义
    0.08
     అనే
    0.08
    inete
    0.08
     కి
    0.08
     Winners
    0.08
     అంశ
    0.08
     కు
    0.08
    Activations Density 0.009%

    No Known Activations