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. 65862
    Prev
    Next
    INDEX
    Explanations

    kindness

    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
     fabricantes
    -0.08
     scherp
    -0.08
     pag
    -0.08
    乱码
    -0.08
     derby
    -0.08
     суш
    -0.08
     PLL
    -0.08
    分页
    -0.08
     fullscreen
    -0.08
     Annual
    -0.07
    POSITIVE LOGITS
     altru
    0.20
     kindness
    0.18
     generosity
    0.17
     gratitude
    0.13
     charity
    0.12
     reciproc
    0.12
    赠
    0.12
     generously
    0.12
     volunteering
    0.12
    慈
    0.12
    Activations Density 0.065%

    No Known Activations