© 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. 19-RESID-POST-AA
    11. 18798
    Prev
    Next
    INDEX
    Explanations

    202

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abilis
    -0.10
     буквально
    -0.09
     experimented
    -0.09
    ”?↵↵
    -0.09
     například
    -0.09
     också
    -0.09
     ook
    -0.09
    .nome
    -0.09
     некоторое
    -0.09
     unul
    -0.09
    POSITIVE LOGITS
     updated
    0.16
    (updated
    0.15
     업데이트
    0.15
    updated
    0.14
    最新版
    0.14
     revised
    0.14
     Updated
    0.14
    Updated
    0.14
    _updated
    0.13
     अपडेट
    0.13
    Activations Density 0.012%

    No Known Activations