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. 27248
    Prev
    Next
    INDEX
    Explanations

    Numbers related to 1

    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
     breasts
    -0.08
    ubert
    -0.08
     Sujet
    -0.08
     sizable
    -0.08
     Федерации
    -0.07
     Rockies
    -0.07
    Boards
    -0.07
    ੂਰ
    -0.07
     изделия
    -0.07
     Parti
    -0.07
    POSITIVE LOGITS
     življen
    0.10
     حياته
    0.09
     जीवन
    0.08
     ജീവിത
    0.08
     ndụ
    0.08
     حياة
    0.08
     வாழ
    0.08
     జీవ
    0.08
     jeho
    0.08
     જીવન
    0.08
    Activations Density 0.005%

    No Known Activations