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. 120228
    Prev
    Next
    INDEX
    Explanations

    non-violent communication

    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
     Metall
    -0.07
     Metal
    -0.07
     Graphics
    -0.07
    ്രീ
    -0.07
     geology
    -0.07
     neug
    -0.07
     (!
    -0.07
    ох
    -0.07
     ns
    -0.07
    Metal
    -0.07
    POSITIVE LOGITS
     compassionate
    0.09
     empat
    0.09
     interpersonal
    0.08
     гуман
    0.08
     접
    0.08
    نوات
    0.08
    Contacto
    0.08
    acar
    0.08
    ustomed
    0.08
    遣
    0.08
    Activations Density 0.001%

    No Known Activations