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. 7-RESID-POST-AA
    6. 131047
    Prev
    Next
    INDEX
    Explanations

    端

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .fore
    -0.08
    wol
    -0.08
    خر
    -0.08
     Vir
    -0.08
     arre
    -0.07
     Tomas
    -0.07
     presidential
    -0.07
    Vir
    -0.07
    _fore
    -0.07
     vir
    -0.07
    POSITIVE LOGITS
    	yield
    0.08
    Measure
    0.08
     piz
    0.07
     Clearly
    0.07
     Kang
    0.07
    	Read
    0.07
     dbg
    0.07
     lector
    0.07
     REGION
    0.07
     diagn
    0.07
    Activations Density 0.000%

    No Known Activations