© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103048
    Prev
    Next
    INDEX
    Explanations

    morality

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shutterstock
    -0.12
     Docker
    -0.11
     Airbus
    -0.10
     billed
    -0.10
     Hurricane
    -0.10
     GPU
    -0.10
     edgy
    -0.09
     deton
    -0.09
     Radeon
    -0.09
     GPUs
    -0.09
    POSITIVE LOGITS
     moral
    0.16
     воспит
    0.16
     filial
    0.15
     اخلاق
    0.15
     virtues
    0.15
     morality
    0.15
     мораль
    0.14
     teachings
    0.14
    教育
    0.14
    徳
    0.14
    Activations Density 0.011%

    No Known Activations