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. 119306
    Prev
    Next
    INDEX
    Explanations

    =

    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
     effort
    -0.09
     convertirse
    -0.08
     ál
    -0.08
    ooter
    -0.07
     mâ
    -0.07
     pupils
    -0.07
     hij
    -0.07
    让我
    -0.07
    怎样
    -0.07
     Miley
    -0.07
    POSITIVE LOGITS
    นะ
    0.07
    기업
    0.07
    .nom
    0.07
     tvor
    0.07
     Roz
    0.07
     aceite
    0.07
    िट
    0.07
     పరి�
    0.07
    hy
    0.07
    [Serialize
    0.07
    Activations Density 0.006%

    No Known Activations