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. 9173
    Prev
    Next
    INDEX
    Explanations

    ADC

    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
     printed
    -0.08
     forgiven
    -0.08
     toe
    -0.08
     valued
    -0.07
    ers
    -0.07
     styled
    -0.07
     Terry
    -0.07
     steril
    -0.07
    lent
    -0.07
     SSI
    -0.07
    POSITIVE LOGITS
    .Results
    0.08
    .normalize
    0.07
     Huge
    0.07
     feugiat
    0.07
    主营
    0.07
    irge
    0.07
     rn
    0.07
    cum
    0.07
     buryo
    0.07
    ்கு
    0.07
    Activations Density 0.000%

    No Known Activations