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. 23-RESID-POST-AA
    6. 130964
    Prev
    Next
    INDEX
    Explanations

    unknown character

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     promos
    -0.08
     dense
    -0.08
    Dense
    -0.08
    Sharing
    -0.07
    -density
    -0.07
    Dl
    -0.07
    елі
    -0.07
    :u
    -0.07
     Dense
    -0.07
    dense
    -0.07
    POSITIVE LOGITS
     funcionando
    0.09
    krivelse
    0.08
    ्भ
    0.08
    осуд
    0.08
     funcionamento
    0.08
    рабатывать
    0.08
     recognizable
    0.08
     mejoras
    0.08
     عملکرد
    0.08
     функциони
    0.08
    Activations Density 0.001%

    No Known Activations