© 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. 50821
    Prev
    Next
    INDEX
    Explanations

    be

    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
     mindestens
    -0.09
     spätestens
    -0.08
     imprescindible
    -0.08
     USING
    -0.08
     Cannot
    -0.08
     करेंगे
    -0.08
     unmistak
    -0.07
     unquestionably
    -0.07
     would
    -0.07
    ईल
    -0.07
    POSITIVE LOGITS
     akár
    0.21
     various
    0.19
     possibly
    0.17
    Various
    0.17
     įvair
    0.16
     sometimes
    0.16
    possibly
    0.16
     arbitrary
    0.16
     çeşitli
    0.16
     anywhere
    0.16
    Activations Density 0.187%

    No Known Activations