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. 43435
    Prev
    Next
    INDEX
    Explanations

    Breathing techniques

    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
     
    -0.08
     Philip
    -0.07
     Price
    -0.07
    hausen
    -0.07
     Items
    -0.07
     prob
    -0.07
     chess
    -0.07
    (serial
    -0.06
     of
    -0.06
     serialized
    -0.06
    POSITIVE LOGITS
     diaphr
    0.11
     abdominal
    0.11
     täiel
    0.11
     возду
    0.10
     abdomen
    0.10
    全过程
    0.09
     plenamente
    0.09
    Fullscreen
    0.09
     поў
    0.09
     belly
    0.09
    Activations Density 0.008%

    No Known Activations