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. 65221
    Prev
    Next
    INDEX
    Explanations

    Paulo Freire

    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
    >S
    -0.08
    <li
    -0.08
    Laugh
    -0.08
    numerusform
    -0.07
     apr
    -0.07
     Valentine's
    -0.07
    apr
    -0.07
     comedian
    -0.07
     חלק
    -0.07
    ਾਜ
    -0.07
    POSITIVE LOGITS
     cauliflower
    0.09
     reeks
    0.08
     dagger
    0.08
    Tha
    0.08
     wacht
    0.08
    ZG
    0.07
     ress
    0.07
     wyth
    0.07
     Basel
    0.07
    own
    0.07
    Activations Density 0.000%

    No Known Activations