© 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. 19-RESID-POST-AA
    11. 18460
    Prev
    Next
    INDEX
    Explanations

    say number 7

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ிற
    -0.09
    probably
    -0.08
    <?
    -0.08
     probably
    -0.08
     kyse
    -0.08
     hynny
    -0.08
     probablement
    -0.08
     שזה
    -0.08
    that
    -0.08
     That
    -0.07
    POSITIVE LOGITS
     complementary
    0.08
    +self
    0.07
     करीब
    0.07
    onderzoek
    0.07
     протяжении
    0.07
     ввод
    0.07
    *object
    0.07
     ಅವಕಾಶ
    0.07
    .io
    0.07
    -generated
    0.07
    Activations Density 0.003%

    No Known Activations