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. 120152
    Prev
    Next
    INDEX
    Explanations

    proving theorems

    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
     low
    -0.07
     gim
    -0.07
     categor
    -0.07
    ాన
    -0.07
     description
    -0.07
    /software
    -0.07
     {\
    -0.07
     lo
    -0.07
    ాని
    -0.07
     megh
    -0.07
    POSITIVE LOGITS
     qen
    0.09
     sentidos
    0.08
     entlang
    0.08
     книга
    0.08
     യുവ
    0.08
     पुस्त
    0.08
    ارك
    0.08
    "io
    0.08
     triangles
    0.08
    uction
    0.08
    Activations Density 0.008%

    No Known Activations