© 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. 69063
    Prev
    Next
    INDEX
    Explanations

    the

    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
     uphe
    -0.08
     mesurer
    -0.08
     Climate
    -0.07
    මා
    -0.07
     TIMES
    -0.07
    -0.07
     mea
    -0.07
     Measuring
    -0.07
     climate
    -0.07
    .err
    -0.07
    POSITIVE LOGITS
     пациента
    0.10
    流
    0.09
    Paciente
    0.09
     prácticas
    0.08
    珠
    0.08
     любит
    0.08
     య
    0.08
    prakt
    0.08
     пациент
    0.08
    護士
    0.08
    Activations Density 0.006%
    No Known Activations