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. 120253
    Prev
    Next
    INDEX
    Explanations

    vi

    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
     spiritual
    -0.08
     특별
    -0.08
     де
    -0.07
     세
    -0.07
    Rain
    -0.07
     WI
    -0.07
    .program
    -0.07
     screen
    -0.07
    .screen
    -0.07
     수
    -0.07
    POSITIVE LOGITS
    حاد
    0.09
     outbreaks
    0.08
    万辆
    0.08
     adjoining
    0.08
    0.08
     coy
    0.08
    _pid
    0.08
    东县
    0.08
     evolving
    0.08
     siku
    0.08
    Activations Density 0.001%

    No Known Activations