© 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. 23-RESID-POST-AA
    11. 49689
    Prev
    Next
    INDEX
    Explanations

    essay

    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
     saber
    -0.09
     mentions
    -0.08
     screamed
    -0.08
     знаете
    -0.08
     Mention
    -0.08
     عَل
    -0.08
     示例
    -0.08
     FIND
    -0.08
     whispers
    -0.08
     knowing
    -0.08
    POSITIVE LOGITS
     tracing
    0.17
     illuminate
    0.17
     unpack
    0.17
     dissect
    0.16
     chart
    0.16
     elucid
    0.16
     scrutin
    0.16
     examine
    0.16
     traced
    0.16
    Tracing
    0.15
    Activations Density 0.056%

    No Known Activations