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. 112288
    Prev
    Next
    INDEX
    Explanations

    asterisk symbol

    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
    Meng
    -0.11
     Meng
    -0.08
    Away
    -0.08
    Lastly
    -0.08
    �
    -0.08
    essione
    -0.07
    -0.07
     explained
    -0.07
    EM
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     تحت
    0.07
     TSR
    0.07
     QS
    0.07
     inger
    0.07
     sür
    0.07
     bire
    0.07
    workspace
    0.07
     кай
    0.07
     workspace
    0.07
     Immer
    0.07
    Activations Density 0.015%

    No Known Activations