Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 120150
    Prev
    Next
    INDEX
    Explanations

    speech and lip reading

    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
     LUA
    -0.09
     lua
    -0.08
    (layer
    -0.08
    גר
    -0.08
     Lua
    -0.07
    ಬೇಕ
    -0.07
    ализ
    -0.07
    /km
    -0.07
    ensation
    -0.07
    Closure
    -0.07
    POSITIVE LOGITS
     учитывать
    0.09
     acompanha
    0.09
     humain
    0.08
    陪
    0.08
     teniendo
    0.08
     cep
    0.08
     vig
    0.08
     informado
    0.08
    igir
    0.08
    otro
    0.08
    Activations Density 0.001%

    No Known Activations