© 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. 51642
    Prev
    Next
    INDEX
    Explanations

    b

    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
    ziens
    -0.08
    ROWS
    -0.08
     rolls
    -0.08
    äub
    -0.08
    flows
    -0.07
    ,we
    -0.07
    runs
    -0.07
    {}\
    -0.07
     ym
    -0.07
    weise
    -0.07
    POSITIVE LOGITS
    ury
    0.10
    indrome
    0.10
    ake
    0.09
    ind
    0.09
    an
    0.09
    URY
    0.09
    athe
    0.09
    ंक
    0.08
    inden
    0.08
     marry
    0.08
    Activations Density 0.010%

    No Known Activations