© 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. 23-RESID-POST-AA
    11. 50868
    Prev
    Next
    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
     interrup
    -0.08
    Inner
    -0.08
    Readable
    -0.07
     CAPS
    -0.07
     inquiét
    -0.07
    Dock
    -0.07
     Inner
    -0.07
    Interactor
    -0.07
     interactieve
    -0.07
    POSITIVE LOGITS
    'ai
    0.15
    ’ai
    0.15
    ʻai
    0.14
    soo
    0.12
    soeng
    0.11
    'ak
    0.11
    'aj
    0.11
    ’ek
    0.11
    thawi
    0.11
    ians
    0.11
    Activations Density 0.021%
    No Known Activations