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. 78712
    Prev
    Next
    INDEX
    Explanations

    Base conversions / calculations

    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
     ไล
    -0.09
     Liv
    -0.08
     Lib
    -0.08
     Liber
    -0.08
     कमजोर
    -0.08
     liberar
    -0.08
    .Should
    -0.08
    akers
    -0.08
     Libre
    -0.07
     larg
    -0.07
    POSITIVE LOGITS
     bedding
    0.09
    號
    0.09
     notation
    0.09
     phenomenal
    0.08
    ska
    0.08
    ’-
    0.08
    Notation
    0.08
     quo
    0.08
    (_)
    0.08
    notation
    0.08
    Activations Density 0.009%

    No Known Activations