© 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. 51549
    Prev
    Next
    INDEX
    Explanations

    match

    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
     massive
    -0.09
     Maßnahmen
    -0.08
    후
    -0.07
     мера
    -0.07
    RARY
    -0.07
     matang
    -0.07
    વાર
    -0.07
    .twimg
    -0.07
    షల్
    -0.07
    천
    -0.07
    POSITIVE LOGITS
    ups
    0.17
    sticks
    0.15
    making
    0.15
    -ups
    0.14
    up
    0.13
    maker
    0.13
    -up
    0.13
     pennies
    0.13
    stick
    0.13
    (es
    0.12
    Activations Density 0.030%

    No Known Activations