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. 102912
    Prev
    Next
    INDEX
    Explanations

    code and debugging

    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
     afterwards
    -0.08
    "]))
    -0.07
    教学
    -0.07
    )])
    -0.07
    进去
    -0.07
     кі
    -0.07
     You'll
    -0.07
     şekl
    -0.07
    指导
    -0.07
    ')}}"></
    -0.07
    POSITIVE LOGITS
    (${
    0.10
     ${(
    0.10
     ${
    0.09
     (${
    0.09
     ith
    0.09
    _${
    0.09
    :${
    0.09
     sebesar
    0.09
     {:?
    0.09
     '${
    0.09
    Activations Density 0.010%

    No Known Activations