© 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. 111016
    Prev
    Next
    INDEX
    Explanations

    separate

    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
     misunderstood
    -0.07
     pretty
    -0.07
     أم
    -0.07
    kanı
    -0.07
    atifs
    -0.07
     dink
    -0.07
     meis
    -0.07
    有效
    -0.07
     ness
    -0.07
    adur
    -0.07
    POSITIVE LOGITS
     namens
    0.10
    Another
    0.10
     જુ
    0.09
     અલગ
    0.09
    別
    0.09
     приходит
    0.09
    another
    0.09
     दुस
    0.08
     अर्को
    0.08
     мень
    0.08
    Activations Density 0.078%

    No Known Activations