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

    Neuronpedia

    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. 45631
    Prev
    Next
    INDEX
    Explanations

    careers

    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
     joints
    -0.07
     healing
    -0.07
     retrieval
    -0.07
     cd
    -0.07
     exported
    -0.07
     CD
    -0.07
     aggregated
    -0.07
     Export
    -0.07
     Healing
    -0.07
     multi
    -0.06
    POSITIVE LOGITS
     vocation
    0.12
     nghề
    0.12
    成为
    0.12
     apprenticeship
    0.11
    Become
    0.11
     carrière
    0.11
     deelname
    0.11
     carreira
    0.11
     devenir
    0.10
    Career
    0.10
    Activations Density 0.112%

    No Known Activations