© 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. 23-RESID-POST-AA
    11. 49035
    Prev
    Next
    INDEX
    Explanations

    卡

    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
    gable
    -0.09
    .microsoft
    -0.08
    咖
    -0.08
     الأوسط
    -0.08
    ajaran
    -0.08
    .tell
    -0.08
    OPSIS
    -0.08
    igy
    -0.08
     kiba
    -0.08
     Cubs
    -0.07
    POSITIVE LOGITS
    顿
    0.12
    片
    0.12
    �
    0.10
    住
    0.10
    车
    0.09
    槽
    0.09
    neen
    0.08
    尔
    0.08
    司
    0.08
     мест
    0.08
    Activations Density 0.001%

    No Known Activations