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. 30021
    Prev
    Next
    INDEX
    Explanations

    ley

    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
     PIX
    -0.08
     relacion
    -0.08
     selsk
    -0.08
    岩
    -0.07
     weth
    -0.07
     colesterol
    -0.07
     embl
    -0.07
     suitability
    -0.07
     paylines
    -0.07
     COMPANY
    -0.07
    POSITIVE LOGITS
    letzt
    0.08
    avaa
    0.08
    idos
    0.07
    539
    0.07
    于是
    0.07
     ferramenta
    0.07
    -tool
    0.07
    973
    0.07
    '];?>↵
    0.07
     инф
    0.07
    Activations Density 0.234%

    No Known Activations