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. 119365
    Prev
    Next
    INDEX
    Explanations

    accomplishment and helping others

    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
     рекоменду
    -0.08
     daño
    -0.08
    �
    -0.08
    παν
    -0.08
     Explicit
    -0.08
     spyware
    -0.07
    .Filters
    -0.07
     주장
    -0.07
    訂
    -0.07
    .temperature
    -0.07
    POSITIVE LOGITS
     exhilar
    0.18
     thrill
    0.17
     exhilarating
    0.15
     gratifying
    0.14
     thrills
    0.13
     thrilling
    0.13
     rewarding
    0.13
     আনন্দ
    0.13
     આનંદ
    0.13
     sensação
    0.12
    Activations Density 0.131%

    No Known Activations