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. 88013
    Prev
    Next
    INDEX
    Explanations

    Fannie Mae, menopause, hot flashes

    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
     airline
    -0.08
    air
    -0.08
     بعيد
    -0.08
    Air
    -0.08
    reisen
    -0.08
     air
    -0.07
     adventure
    -0.07
     motorway
    -0.07
    (of
    -0.07
    acity
    -0.07
    POSITIVE LOGITS
     inco
    0.09
     אלע
    0.08
     Ace
    0.08
    卧
    0.08
     九
    0.08
    监督
    0.08
     dépos
    0.07
    说道
    0.07
     കെ
    0.07
    ೇಳ
    0.07
    Activations Density 0.003%

    No Known Activations