Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120114
    Prev
    Next
    INDEX
    Explanations

    Indefinite article ("a")

    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
     esfera
    -0.10
     Castell
    -0.09
     discours
    -0.09
     existência
    -0.09
     іс
    -0.08
    ----------------------------------------------------------------------------
    -0.08
     existencia
    -0.08
     tồn
    -0.08
     berada
    -0.08
     داشته
    -0.08
    POSITIVE LOGITS
    用于
    0.11
     desarrollar
    0.08
     powerful
    0.08
     versatile
    0.08
    .
    0.08
     用
    0.07
    ,用
    0.07
     des
    0.07
    刻
    0.07
     desarrollado
    0.07
    Activations Density 0.016%

    No Known Activations