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. 23069
    Prev
    Next
    INDEX
    Explanations

    fueling

    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
     계
    -0.08
     ditt
    -0.08
    ottom
    -0.08
     inv
    -0.07
    512
    -0.07
    abbit
    -0.07
     항상
    -0.07
    
    -0.07
     Aub
    -0.07
    /account
    -0.07
    POSITIVE LOGITS
    0.10
     fluoride
    0.10
     Metro
    0.09
     methane
    0.09
     mainstream
    0.09
     Trucks
    0.08
    ाइड
    0.08
     gases
    0.08
     Geschäft
    0.08
     trucks
    0.08
    Activations Density 0.004%

    No Known Activations