© 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. 11-RESID-POST-AA
    11. 31361
    Prev
    Next
    INDEX
    Explanations

    endocrine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cs
    -0.08
     rhetorical
    -0.08
     lev
    -0.08
    (Request
    -0.08
     religiosas
    -0.08
    illas
    -0.07
     ls
    -0.07
     rhetoric
    -0.07
     dir
    -0.07
     dealer
    -0.07
    POSITIVE LOGITS
     ect
    0.10
     சாத
    0.09
    _SOURCE
    0.08
     활성
    0.08
     Sach
    0.08
     ಪು
    0.08
     불
    0.08
    集团
    0.07
     generously
    0.07
     sensible
    0.07
    Activations Density 0.001%

    No Known Activations