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. 104174
    Prev
    Next
    INDEX
    Explanations

    The

    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
    enz
    -0.07
    arith
    -0.07
     Herkunft
    -0.07
    EOF
    -0.07
     città
    -0.07
    .BOLD
    -0.07
    ocu
    -0.07
    UES
    -0.07
    ിന്റ
    -0.07
    .math
    -0.07
    POSITIVE LOGITS
     추진
    0.11
     계획
    0.09
     разработки
    0.09
     યોજના
    0.09
     વિકાસ
    0.09
     ambitious
    0.09
    рева
    0.09
     تطوير
    0.09
     developing
    0.09
     proposing
    0.09
    Activations Density 0.054%

    No Known Activations