© 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. 3-RESID-POST-AA
    11. 922
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ypress
    -0.08
     Traders
    -0.08
    _DIFF
    -0.08
    _Control
    -0.08
     Continue
    -0.08
     জয়
    -0.08
     fortsatt
    -0.08
    _WINDOW
    -0.08
    لىرى
    -0.08
    _SCROLL
    -0.08
    POSITIVE LOGITS
    toni
    0.07
     masuk
    0.07
     дру
    0.07
     EM
    0.07
     mend
    0.07
    elin
    0.07
    edev
    0.07
     operations
    0.07
     lét
    0.07
    илия
    0.07
    Activations Density 0.000%

    No Known Activations