© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51656
    Prev
    Next
    INDEX
    Explanations

    integration with existing systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ulong
    -0.09
     المهنية
    -0.08
     tuned
    -0.08
    850
    -0.08
     atuação
    -0.08
     أثناء
    -0.08
    focused
    -0.08
    ond
    -0.08
     planen
    -0.08
    غل
    -0.07
    POSITIVE LOGITS
     Rodrig
    0.08
     cnn
    0.08
     Мат
    0.08
     api
    0.08
     tv
    0.08
     library
    0.08
     Sinh
    0.08
     national
    0.07
     телевиз
    0.07
    财政
    0.07
    Activations Density 0.002%

    No Known Activations