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. 53258
    Prev
    Next
    INDEX
    Explanations

    safety tips

    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
    新浪
    -0.09
     nostalgia
    -0.09
     GDP
    -0.08
    Spotify
    -0.08
     Spotify
    -0.08
    .nodes
    -0.08
    績
    -0.08
    .tax
    -0.08
    .avg
    -0.07
     guilty
    -0.07
    POSITIVE LOGITS
     안전
    0.23
     safety
    0.23
     Safety
    0.22
    Safety
    0.21
     hazards
    0.21
    安全
    0.21
     precautions
    0.21
     নিরাপ
    0.20
    危险
    0.20
     hazardous
    0.20
    Activations Density 0.149%

    No Known Activations