© 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. 19-RESID-POST-AA
    11. 102572
    Prev
    Next
    INDEX
    Explanations

    ar

    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
    /"
    -0.09
    valu
    -0.08
    these
    -0.08
    xref
    -0.08
    like
    -0.08
    …but
    -0.08
    !,
    -0.08
    Pare
    -0.08
    /non
    -0.08
    Construct
    -0.08
    POSITIVE LOGITS
     一诺
    0.12
     环宇
    0.11
     金盾
    0.11
     天逸
    0.11
     天音
    0.11
     太阳城
    0.11
     飞
    0.11
     秒
    0.10
     高升
    0.10
     日日
    0.10
    Activations Density 0.001%

    No Known Activations