© 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. 111094
    Prev
    Next
    INDEX
    Explanations

    geometry/math

    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
     aside
    -0.09
     thus
    -0.08
    Venue
    -0.08
     sendiri
    -0.08
     নিয়
    -0.08
    所以
    -0.07
     cabe
    -0.07
     initializer
    -0.07
     ಪರಿಣಾಮ
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     counterparts
    0.10
     counterpart
    0.10
     Kolleg
    0.08
     سایر
    0.08
     Colonel
    0.08
     అదే
    0.08
    jenige
    0.08
     correspondente
    0.08
    另一
    0.08
     Celui
    0.08
    Activations Density 0.089%

    No Known Activations