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. 43447
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
     experimentation
    -0.08
     entr
    -0.08
     jaune
    -0.08
     alasan
    -0.08
     चेहरे
    -0.08
     الضوء
    -0.08
     tọ
    -0.08
    -0.08
     author
    -0.08
     प्रकाश
    -0.08
    POSITIVE LOGITS
    poly
    0.08
    _pipe
    0.08
     Hick
    0.08
    pipe
    0.08
     Poly
    0.08
     narrowing
    0.08
    ikelihood
    0.08
    Poly
    0.07
    _output
    0.07
    sstream
    0.07
    Activations Density 0.004%

    No Known Activations