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. 30509
    Prev
    Next
    INDEX
    Explanations

    ney

    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
     arrep
    -0.08
     संग्रह
    -0.08
    -tem
    -0.08
     meteor
    -0.08
     Irr
    -0.07
     Fiat
    -0.07
     culturally
    -0.07
    IRT
    -0.07
    iom
    -0.07
     stroll
    -0.07
    POSITIVE LOGITS
     Promotional
    0.09
     promotional
    0.09
     formatting
    0.08
     formulations
    0.08
     attribution
    0.08
    Formatted
    0.08
    投稿
    0.08
     formulation
    0.08
     attente
    0.07
     etiquette
    0.07
    Activations Density 0.008%

    No Known Activations