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. 49250
    Prev
    Next
    INDEX
    Explanations

    Image processing architectures

    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
     Bukkit
    -0.08
     scattering
    -0.07
     interpersonal
    -0.07
    449
    -0.07
    oll
    -0.07
     questionnaire
    -0.07
    190
    -0.07
    191
    -0.07
    는
    -0.07
    ువ
    -0.07
    POSITIVE LOGITS
    _lvl
    0.09
     ана
    0.09
     ઘટાડ
    0.09
     жоғ
    0.09
     четвер
    0.09
     высокой
    0.08
    -final
    0.08
    (/^
    0.08
     вниз
    0.08
     Gast
    0.08
    Activations Density 0.001%

    No Known Activations