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. 65272
    Prev
    Next
    INDEX
    Explanations

    use

    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
     jpg
    -0.08
     comforting
    -0.07
     donn
    -0.07
    �
    -0.07
    究
    -0.07
     marrow
    -0.07
     indoors
    -0.07
    鲜
    -0.07
    になる
    -0.07
    なお
    -0.07
    POSITIVE LOGITS
     mok
    0.07
    0.07
     jj
    0.07
     �
    0.07
    ippy
    0.07
     Tres
    0.07
     machine
    0.07
     पैर
    0.07
     اول
    0.07
     filesystem
    0.07
    Activations Density 0.035%

    No Known Activations