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. 65719
    Prev
    Next
    INDEX
    Explanations

    number

    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
     rất
    -0.09
     pillar
    -0.09
     pur
    -0.08
     stark
    -0.08
     pillars
    -0.07
     выгляд
    -0.07
     muito
    -0.07
    빠
    -0.07
     väldigt
    -0.07
     நடை
    -0.07
    POSITIVE LOGITS
    是多少
    0.10
    /count
    0.09
    ifer
    0.08
    lend
    0.08
    ogh
    0.08
    lomer
    0.08
    -duration
    0.08
     thereof
    0.08
     bort
    0.07
     문자열
    0.07
    Activations Density 0.025%

    No Known Activations