© 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. 7-RESID-POST-AA
    11. 1036
    Prev
    Next
    INDEX
    Explanations

    robotics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _tiles
    -0.09
    ening
    -0.08
    mán
    -0.08
    irar
    -0.08
    Clark
    -0.08
     tiled
    -0.08
    -after
    -0.08
     depicted
    -0.08
     tubes
    -0.08
    区别
    -0.07
    POSITIVE LOGITS
    _arm
    0.09
     precision
    0.08
     Natasha
    0.08
     arm
    0.08
    ,:
    0.08
     jus
    0.08
     arms
    0.07
    -assisted
    0.07
    737
    0.07
    portfolio
    0.07
    Activations Density 0.006%

    No Known Activations