© 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. 19-RESID-POST-AA
    11. 20436
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    一区二区
    -0.10
    定胆
    -0.10
    不了怎么办
    -0.10
    久久久
    -0.10
     აცხადებს
    -0.09
    黄网站
    -0.09
    ებაა
    -0.09
     თავმჯდომ
    -0.09
    级毛片
    -0.09
    分时时彩
    -0.09
    POSITIVE LOGITS
     Then
    0.15
    Then
    0.13
    然后
    0.13
     To
    0.13
     Тогда
    0.12
    Usage
    0.12
     usage
    0.12
     Luego
    0.11
    。そして
    0.11
     vervolgens
    0.11
    Activations Density 0.019%

    No Known Activations