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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 30696
    Prev
    Next
    INDEX
    Explanations

    art/product photography descriptions

    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
    partum
    -0.09
     welfare
    -0.09
     pension
    -0.08
    .join
    -0.08
     hardships
    -0.08
    情况
    -0.08
     refugee
    -0.08
     malaria
    -0.08
    elfare
    -0.07
    (join
    -0.07
    POSITIVE LOGITS
    纹
    0.10
     embossed
    0.10
     Glow
    0.09
     Measurements
    0.09
     measurements
    0.09
     Resin
    0.09
     photographed
    0.09
     fotograf
    0.09
     Metallic
    0.09
     tactile
    0.09
    Activations Density 0.049%

    No Known Activations