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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120266
    Prev
    Next
    INDEX
    Explanations

    self-discipline and integrity

    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
     ach
    -0.09
     Engine
    -0.08
    _IMPLEMENT
    -0.08
     different
    -0.08
     studs
    -0.08
    .Engine
    -0.08
     nod
    -0.07
     nummer
    -0.07
     Numer
    -0.07
    種類
    -0.07
    POSITIVE LOGITS
    income
    0.08
     disclosures
    0.08
     biographies
    0.08
    意识
    0.08
     selfies
    0.08
    Declaration
    0.08
     lifestyles
    0.08
     visitas
    0.08
    Lifestyle
    0.08
    巡视
    0.08
    Activations Density 0.007%

    No Known Activations