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. 11735
    Prev
    Next
    INDEX
    Explanations

    chemical synthesis

    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
     welcomes
    -0.09
     வீர
    -0.09
     vaccinations
    -0.09
     언제
    -0.08
     autoplay
    -0.08
     IMPLEMENT
    -0.08
     combats
    -0.08
     flips
    -0.08
     glitches
    -0.08
    iun
    -0.08
    POSITIVE LOGITS
     acid
    0.12
     benz
    0.12
     ester
    0.11
     derivatives
    0.11
    ethyl
    0.11
     acids
    0.11
     compounds
    0.11
     arom
    0.10
     alk
    0.10
     radicals
    0.10
    Activations Density 0.013%

    No Known Activations