© 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. 21929
    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
    The
    -0.15
    This
    -0.15
    When
    -0.14
    Their
    -0.14
    Given
    -0.14
    They
    -0.14
    Because
    -0.14
    Instead
    -0.13
    Here's
    -0.13
    These
    -0.13
    POSITIVE LOGITS
     在
    0.21
     如果
    0.21
     微信上
    0.21
     若
    0.19
     蓝盾
    0.19
     正点
    0.19
     是否
    0.19
     狠狠
    0.18
     高登
    0.18
     初始化
    0.18
    Activations Density 0.032%

    No Known Activations