© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 64886
    Prev
    Next
    INDEX
    Explanations

    heets

    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
     للغاية
    -0.08
     yourself
    -0.08
    lover
    -0.08
    istically
    -0.08
    -yourself
    -0.07
     kayan
    -0.07
     habilidades
    -0.07
    lysninger
    -0.07
    ställ
    -0.07
    ancode
    -0.07
    POSITIVE LOGITS
    列表
    0.09
    .named
    0.08
     شم
    0.08
    :not
    0.08
    .remove
    0.08
    涯
    0.08
    (scope
    0.07
    [source
    0.07
    源
    0.07
     তাল
    0.07
    Activations Density 0.004%

    No Known Activations