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. 120452
    Prev
    Next
    INDEX
    Explanations

    GPT

    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
    -0.09
    权益
    -0.08
    ład
    -0.08
    archar
    -0.08
     quasi
    -0.08
     meaningful
    -0.07
     ambul
    -0.07
    群众
    -0.07
     Libert
    -0.07
     Eigent
    -0.07
    POSITIVE LOGITS
     Anth
    0.09
     conversational
    0.08
     જેવા
    0.08
     Bobby
    0.08
     sandbox
    0.08
     чат
    0.08
    /Open
    0.07
    /N
    0.07
     જેવી
    0.07
    ognitive
    0.07
    Activations Density 0.005%

    No Known Activations