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. 30680
    Prev
    Next
    INDEX
    Explanations

    both

    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
     Grund
    -0.08
    terne
    -0.08
    -theme
    -0.08
    twig
    -0.08
     twig
    -0.08
    ullah
    -0.08
    ぐ
    -0.08
     Leslie
    -0.08
     Fine
    -0.08
     jar
    -0.08
    POSITIVE LOGITS
     मनोर
    0.08
     shallow
    0.08
    ыя
    0.08
     porta
    0.08
     entertaining
    0.08
     necessity
    0.08
     সাধ
    0.07
     promote
    0.07
     causa
    0.07
    एक
    0.07
    Activations Density 0.022%

    No Known Activations