Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112069
    Prev
    Next
    INDEX
    Explanations

    /lib

    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
    venu
    -0.08
    genoot
    -0.08
    aniro
    -0.07
     /*
    ↵
    -0.07
     imprime
    -0.07
     sprawling
    -0.07
     Teil
    -0.07
     vast
    -0.07
     tegem
    -0.07
     стало
    -0.07
    POSITIVE LOGITS
     fullness
    0.08
                       ↵
    0.08
    การ
    0.07
     luggage
    0.07
    _DMA
    0.07
     docker
    0.07
    .icon
    0.07
     Garrett
    0.07
     Dados
    0.07
    .extend
    0.07
    Activations Density 0.001%

    No Known Activations