© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64117
    Prev
    Next
    INDEX
    Explanations

    Labor and childbirth

    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
     공부
    -0.08
     강화
    -0.08
     planning
    -0.08
    planning
    -0.08
     штраф
    -0.08
     왜
    -0.08
    .timeout
    -0.08
     desarrollar
    -0.08
     заман
    -0.08
     prerequisite
    -0.07
    POSITIVE LOGITS
     Congratulations
    0.11
     newborn
    0.11
    Congratulations
    0.11
     congratulations
    0.10
     births
    0.10
     babies
    0.10
     jubil
    0.10
     christ
    0.09
     victorious
    0.09
     congratulate
    0.09
    Activations Density 0.011%

    No Known Activations