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. 42051
    Prev
    Next
    INDEX
    Explanations

    warmth

    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
     sph
    -0.08
     Pinn
    -0.08
     ν
    -0.07
     penny
    -0.07
     Nolan
    -0.07
     صاح
    -0.07
     Pb
    -0.07
    วย
    -0.07
    _ans
    -0.07
     hübs
    -0.07
    POSITIVE LOGITS
     warmth
    0.14
     chaleureux
    0.14
    -hearted
    0.13
     chaleure
    0.12
    hearted
    0.12
     warmly
    0.11
     тепл
    0.11
    馨
    0.11
    暖
    0.11
     kindness
    0.10
    Activations Density 0.020%

    No Known Activations