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. 15-RESID-POST-AA
    6. 122
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .launch
    -0.08
    _launch
    -0.08
    _pass
    -0.07
    irre
    -0.07
    ента
    -0.07
     Refin
    -0.07
    _distance
    -0.07
     Implant
    -0.07
     vermutlich
    -0.07
     Loop
    -0.07
    POSITIVE LOGITS
     individuales
    0.10
     individual
    0.09
     correspondientes
    0.09
     correspondiente
    0.08
    waswo
    0.08
     móti
    0.08
    werhu
    0.08
    േരള
    0.08
      
    0.08
     отдельных
    0.08
    Activations Density 0.011%

    No Known Activations