© 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. 103376
    Prev
    Next
    INDEX
    Explanations

    right-hand-side

    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
    ങ്ങളെ
    -0.09
    或者
    -0.08
    ="";↵
    -0.08
     الخاص
    -0.08
     ternyata
    -0.08
    ANGUAGE
    -0.07
    pls
    -0.07
    സി
    -0.07
    ഐ
    -0.07
     അല്ല
    -0.07
    POSITIVE LOGITS
     involving
    0.11
     involves
    0.10
     using
    0.09
     unless
    0.09
     depending
    0.09
    using
    0.09
     potentially
    0.08
     دارای
    0.08
     with
    0.08
     envolvendo
    0.08
    Activations Density 0.019%

    No Known Activations