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. 9069
    Prev
    Next
    INDEX
    Explanations

    responses

    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
     lär
    -0.08
     Peyton
    -0.08
    Ctor
    -0.07
    -0.07
     Carrera
    -0.07
     wykorzyst
    -0.07
    структ
    -0.07
    ാക്കി
    -0.07
     chol
    -0.07
    Rolling
    -0.07
    POSITIVE LOGITS
     каждого
    0.08
     conversational
    0.08
     барлық
    0.08
     바랍니다
    0.08
     одновременно
    0.08
    /avatar
    0.08
    ન
    0.08
    anför
    0.08
     simultaneously
    0.08
     সমস্ত
    0.08
    Activations Density 0.074%

    No Known Activations