© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 69958
    Prev
    Next
    INDEX
    Explanations

    Bullet points/formatting

    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
    ß
    -0.09
     तथा
    -0.09
     případ
    -0.08
    Julie
    -0.08
     bzw
    -0.08
    football
    -0.08
    elta
    -0.08
    cky
    -0.08
    Regexp
    -0.07
    或者
    -0.07
    POSITIVE LOGITS
     Statement
    0.08
     overview
    0.08
    :value
    0.08
    	value
    0.08
    0.08
     Attribute
    0.07
     Identify
    0.07
     motive
    0.07
    Identify
    0.07
     motivation
    0.07
    Activations Density 0.071%
    No Known Activations