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. 78534
    Prev
    Next
    INDEX
    Explanations

    dead

    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
    备用
    -0.08
     placeholder
    -0.08
    >'+
    -0.08
     spy
    -0.07
     provisional
    -0.07
     Sparrow
    -0.07
     containment
    -0.07
    -0.07
     stabilized
    -0.07
    enders
    -0.07
    POSITIVE LOGITS
    碑
    0.08
    开什么
    0.08
    ritur
    0.08
     sueños
    0.08
     supermercados
    0.08
     segredo
    0.08
     Klassiker
    0.08
    秘
    0.08
     clásicos
    0.08
    Dream
    0.08
    Activations Density 0.001%

    No Known Activations