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. 9213
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     resurf
    -0.08
    idur
    -0.08
    复
    -0.08
    ocidad
    -0.07
    americana
    -0.07
    itai
    -0.07
    quier
    -0.07
     móvil
    -0.07
    启动
    -0.07
     inspiración
    -0.07
    POSITIVE LOGITS
    licher
    0.08
     slight
    0.08
     slightly
    0.08
     nationals
    0.07
    ensors
    0.07
     cliff
    0.07
     analyzer
    0.07
    lichkeiten
    0.07
     provis
    0.07
     tomatoes
    0.07
    Activations Density 0.412%

    No Known Activations