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

    Neuronpedia

    APICircuit 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. 106253
    Prev
    Next
    INDEX
    Explanations

    Atmospheric energy/water extraction

    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
     obst
    -0.10
     annul
    -0.08
     расч
    -0.08
     Concern
    -0.07
    -0.07
     concerned
    -0.07
     রিপোর্ট
    -0.07
     berichtet
    -0.07
    exe
    -0.07
    显示
    -0.07
    POSITIVE LOGITS
     aprovech
    0.12
     exploiting
    0.11
     harvesting
    0.10
     harvested
    0.10
    .pool
    0.10
    .available
    0.10
    利用
    0.10
    Harness
    0.09
     harness
    0.09
     aprovechar
    0.09
    Activations Density 0.022%

    No Known Activations