© 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. 113378
    Prev
    Next
    INDEX
    Explanations

    subjects

    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
    Contour
    -0.09
     contour
    -0.08
    ár
    -0.08
     клиентов
    -0.08
    ône
    -0.07
     Amazon
    -0.07
    Estados
    -0.07
    clus
    -0.07
     आत
    -0.07
     Airbnb
    -0.07
    POSITIVE LOGITS
     GCSE
    0.13
    成绩
    0.12
     compulsory
    0.12
     disciplinas
    0.11
     дисцип
    0.11
     electives
    0.11
     discipline
    0.11
     extracurricular
    0.11
    考试
    0.10
    小学
    0.10
    Activations Density 0.021%

    No Known Activations