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. 113992
    Prev
    Next
    INDEX
    Explanations

    resale

    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
    rail
    -0.08
    .literal
    -0.08
    !”
    -0.07
     woven
    -0.07
    :”
    -0.07
     использовать
    -0.07
    势
    -0.07
     pemain
    -0.07
     banned
    -0.07
    AI
    -0.07
    POSITIVE LOGITS
     xml
    0.09
    上午
    0.08
    طم
    0.08
    턴
    0.08
     шп
    0.07
    .Refresh
    0.07
     pronto
    0.07
     agrav
    0.07
     приобр
    0.07
     Master's
    0.07
    Activations Density 0.002%

    No Known Activations