© 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. 15-RESID-POST-AA
    11. 16309
    Prev
    Next
    INDEX
    Explanations

    distance

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kiuj
    -0.11
    იტან
    -0.11
     pornos
    -0.10
    在线观看视频
    -0.10
    在线视频观看
    -0.10
     poved
    -0.10
    -亚洲
    -0.10
    ")+"
    -0.10
    ამც
    -0.10
    免费观看视频
    -0.10
    POSITIVE LOGITS
     =
    0.13
     =↵
    0.10
     new
    0.09
    _new
    0.08
    _re
    0.08
    Demo
    0.08
     (
    0.08
     :=
    0.08
    :
    0.07
    _des
    0.07
    Activations Density 0.035%

    No Known Activations