© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96667
    Prev
    Next
    INDEX
    Explanations

    Variations of "count"

    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
    _guess
    -0.07
     flight
    -0.07
     vaihe
    -0.07
    �西
    -0.07
    -0.07
     Lein
    -0.07
    кия
    -0.07
    ่ม
    -0.07
     عملکرد
    -0.07
     apan
    -0.07
    POSITIVE LOGITS
     cuentan
    0.23
     cuenta
    0.22
     contó
    0.21
     contará
    0.20
     contamos
    0.20
     Cuenta
    0.20
     Conta
    0.20
     conta
    0.19
    Cuenta
    0.19
     contar
    0.19
    Activations Density 0.030%

    No Known Activations