© 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. 23-RESID-POST-AA
    11. 97497
    Prev
    Next
    INDEX
    Explanations

    抱

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ature
    -0.09
     with
    -0.09
     via
    -0.09
    etype
    -0.08
    ée
    -0.08
     more
    -0.08
     by
    -0.08
     set
    -0.08
     for
    -0.08
    nement
    -0.08
    POSITIVE LOGITS
    歉
    0.15
    错误
    0.10
     mild
    0.10
    Lewis
    0.09
    刘
    0.09
    巴
    0.09
    (segment
    0.09
    Donalds
    0.09
     ভুল
    0.09
     hlub
    0.08
    Activations Density 0.007%

    No Known Activations