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. 15-RESID-POST-AA
    6. 19286
    Prev
    Next
    INDEX
    Explanations

    ..

    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
     twg
    -0.08
    (EIF
    -0.08
    orestation
    -0.08
    (groups
    -0.08
    xes
    -0.07
    czema
    -0.07
    ttet
    -0.07
    armaceutical
    -0.07
    (create
    -0.07
     bijna
    -0.07
    POSITIVE LOGITS
    প্র
    0.09
    पर
    0.09
     vamos
    0.08
    সং
    0.08
     porcent
    0.08
     nós
    0.08
     Nós
    0.08
    ূর্ণ
    0.08
     somos
    0.08
    শেষ
    0.08
    Activations Density 0.001%

    No Known Activations