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. 44998
    Prev
    Next
    INDEX
    Explanations

    public safety

    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
     paysages
    -0.08
     inland
    -0.08
    Merk
    -0.08
     criticizing
    -0.08
     түс
    -0.08
    FFER
    -0.07
     understanding
    -0.07
    Sparse
    -0.07
    Understanding
    -0.07
    Smoke
    -0.07
    POSITIVE LOGITS
     Dangerous
    0.11
     dangerous
    0.11
    danger
    0.11
     vile
    0.09
    危险
    0.09
     convicted
    0.09
    -danger
    0.09
     ameaça
    0.09
     unsafe
    0.09
    ,'"
    0.09
    Activations Density 0.053%

    No Known Activations