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. 102922
    Prev
    Next
    INDEX
    Explanations

    product availability notification

    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
     paralysis
    -0.09
     flood
    -0.08
    ively
    -0.08
    orl
    -0.07
    íbr
    -0.07
     avanç
    -0.07
    ;;
    -0.07
     نشر
    -0.07
    verture
    -0.07
     literature
    -0.07
    POSITIVE LOGITS
    [{
    0.08
     ending
    0.08
     Nullable
    0.08
    _est
    0.08
     Array
    0.07
    สบ
    0.07
    zum
    0.07
    าหาร
    0.07
     одеж
    0.07
    ของ
    0.07
    Activations Density 0.002%

    No Known Activations