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. 59780
    Prev
    Next
    INDEX
    Explanations

    plans and ideas

    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
     soziale
    -0.09
     sociais
    -0.09
     الاجتماعية
    -0.09
     സാമൂഹ
    -0.08
     ontvang
    -0.08
    FEATURE
    -0.08
     സോഷ്യ
    -0.08
    .social
    -0.08
     财富
    -0.08
     tere
    -0.08
    POSITIVE LOGITS
     accesor
    0.07
     облад
    0.07
    告诉
    0.07
     قوله
    0.07
     заявил
    0.07
     here
    0.07
     shorthand
    0.07
     accessor
    0.07
     তাই
    0.07
     তাকে
    0.07
    Activations Density 0.011%

    No Known Activations