© 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. 95452
    Prev
    Next
    INDEX
    Explanations

    detective mystery stories

    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
     активности
    -0.08
     나타
    -0.08
     포함
    -0.08
     koma
    -0.08
     managers
    -0.08
    ствен
    -0.07
     글로벌
    -0.07
     modernen
    -0.07
     실행
    -0.07
    -cons
    -0.07
    POSITIVE LOGITS
     মাম
    0.10
     তদন্ত
    0.09
     pie
    0.08
     Oz
    0.08
     lossen
    0.08
     gestalt
    0.08
    案件
    0.08
     cynical
    0.08
     dov
    0.08
     anfangen
    0.08
    Activations Density 0.023%

    No Known Activations