© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 49185
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    ３０
    -0.13
     দ্বিতীয়
    -0.12
    ００
    -0.11
    ２００
    -0.11
    　二
    -0.11
     രണ്ടാം
    -0.11
    ２０
    -0.10
    ５０
    -0.10
     vierde
    -0.10
    ۰۰
    -0.10
    POSITIVE LOGITS
    powers
    0.13
    this
    0.13
    power
    0.12
    a
    0.12
    p
    0.12
    i
    0.12
    given
    0.12
    specific
    0.11
    k
    0.11
    chosen
    0.11
    Activations Density 0.075%

    No Known Activations