© 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. 18751
    Prev
    Next
    INDEX
    Explanations

    question mark

    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
     zwei
    -0.08
     upang
    -0.08
     możemy
    -0.08
     hvis
    -0.08
     jeśli
    -0.08
     omdat
    -0.08
    rijf
    -0.08
     eftersom
    -0.08
     iji
    -0.08
    combine
    -0.08
    POSITIVE LOGITS
    事实上
    0.12
     actually
    0.12
    Actually
    0.12
     Actually
    0.12
     historically
    0.11
    据了解
    0.11
     unsure
    0.11
     Indeed
    0.11
    实际上
    0.11
     I'm
    0.11
    Activations Density 0.083%

    No Known Activations