© 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. 64651
    Prev
    Next
    INDEX
    Explanations

    loan

    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
     nangang
    -0.09
    ;)↵↵
    -0.08
    tuple
    -0.08
     своё
    -0.08
    оре
    -0.08
     nawe
    -0.08
    Ζ
    -0.08
     caret
    -0.08
     precaution
    -0.08
     tuple
    -0.08
    POSITIVE LOGITS
     disappeared
    0.08
     norm
    0.08
    _norm
    0.07
    orm
    0.07
     Glad
    0.07
     Ma
    0.07
    Norm
    0.07
    .peek
    0.07
    атом
    0.07
     Norm
    0.07
    Activations Density 0.000%

    No Known Activations