© 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. 18982
    Prev
    Next
    INDEX
    Explanations

    period

    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
     of
    -0.09
     linear
    -0.09
     if
    -0.08
     visually
    -0.08
    linear
    -0.08
     =
    -0.08
     philosophy
    -0.08
     or
    -0.08
    .linear
    -0.08
    ,
    -0.08
    POSITIVE LOGITS
    　据
    0.13
    报道称
    0.13
    （记者
    0.13
     Reuters
    0.12
    相关新闻
    0.12
    Reuters
    0.12
    中新网
    0.11
    报道
    0.11
     сообщили
    0.11
    ၂၀
    0.11
    Activations Density 0.276%

    No Known Activations