© 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. 49803
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     största
    -0.08
    genomen
    -0.08
    iek
    -0.08
    uch
    -0.08
    hatan
    -0.08
    -specific
    -0.07
     وظيفة
    -0.07
    ichtigen
    -0.07
    agut
    -0.07
     אַר
    -0.07
    POSITIVE LOGITS
    ・・・↵
    0.14
    ・・・↵↵
    0.13
     ...↵↵
    0.13
     ...↵
    0.13
     વગેરે
    0.12
    ....
    0.12
    .......
    0.12
    ....↵↵
    0.12
    ..?
    0.12
    ・・・
    0.12
    Activations Density 0.038%

    No Known Activations