© 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 EvalsExportsAPI 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. 49888
    Prev
    Next
    INDEX
    Explanations

    say numbers

    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
    =<
    -0.13
     প্রদান
    -0.11
     প্রতিষ্ঠান
    -0.11
     সংশ
    -0.10
     արժեք
    -0.10
     পৃথ
    -0.10
     ggf
    -0.10
     рекомен
    -0.10
     համապատասխան
    -0.10
     nqa
    -0.10
    POSITIVE LOGITS
    999
    0.17
     terrifying
    0.14
    疯狂
    0.14
     Forever
    0.14
    Forever
    0.14
     endless
    0.14
    666
    0.13
     Fuck
    0.13
     天堂
    0.13
    99
    0.13
    Activations Density 0.057%

    No Known Activations