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. 120220
    Prev
    Next
    INDEX
    Explanations

    Code or instructions provider

    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
     acompanhamento
    -0.09
     пош
    -0.09
     adn
    -0.09
     DOWNLOAD
    -0.07
     VARIABLE
    -0.07
     يرج
    -0.07
     HEADER
    -0.07
    <Key
    -0.07
     Atendimento
    -0.07
    -Pl
    -0.07
    POSITIVE LOGITS
     gyms
    0.09
     firms
    0.08
     besitzen
    0.08
     обла
    0.08
    lares
    0.08
     मालिक
    0.08
    افته
    0.07
     garages
    0.07
    яш
    0.07
    局
    0.07
    Activations Density 0.000%

    No Known Activations