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. 49367
    Prev
    Next
    INDEX
    Explanations

    Getting Things Done (GTD)

    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
     slad
    -0.08
     pula
    -0.08
     രേഖ
    -0.07
     ક્લ
    -0.07
     બાળક
    -0.07
     springfox
    -0.07
     conventions
    -0.07
     ക്ല
    -0.07
     alty
    -0.07
     તમામ
    -0.07
    POSITIVE LOGITS
    ۲۰
    0.09
    LEAR
    0.08
    ukke
    0.08
    CARE
    0.08
    Ә
    0.08
     geeign
    0.08
    wealth
    0.08
     Shepherd
    0.08
     Harr
    0.08
     lecturer
    0.08
    Activations Density 0.002%

    No Known Activations