© 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. 25152
    Prev
    Next
    INDEX
    Explanations

    standard

    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
     blanca
    -0.09
     whiten
    -0.08
    preh
    -0.08
     waw
    -0.08
     truc
    -0.08
     nuk
    -0.08
    ainn
    -0.07
    552
    -0.07
    29
    -0.07
     સફ
    -0.07
    POSITIVE LOGITS
    그리고
    0.08
     MMC
    0.08
     Thành
    0.08
     Holl
    0.07
     Lev
    0.07
    _INFORMATION
    0.07
    _UINT
    0.07
    _SUCCESS
    0.07
     giorno
    0.07
    ьми
    0.07
    Activations Density 0.000%

    No Known Activations