Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97973
    Prev
    Next
    INDEX
    Explanations

    generosity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _PLL
    -0.08
     PLL
    -0.08
    PLL
    -0.08
    вой
    -0.07
     aufreg
    -0.07
    348
    -0.07
    走势
    -0.07
     pll
    -0.07
    .escape
    -0.07
     avion
    -0.07
    POSITIVE LOGITS
     generosity
    0.29
     kindness
    0.29
     altru
    0.26
     charitable
    0.22
     acts
    0.22
     großzüg
    0.21
     philanth
    0.21
     charity
    0.21
     generous
    0.21
     actos
    0.21
    Activations Density 0.105%

    No Known Activations