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. 58878
    Prev
    Next
    INDEX
    Explanations

    rhythmic speech, hypnosis

    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
    _bitmap
    -0.09
     sheds
    -0.09
    -chart
    -0.09
     Jets
    -0.08
     fireworks
    -0.08
     wishlist
    -0.08
     erupted
    -0.08
     berth
    -0.08
     Apert
    -0.08
     Kirchen
    -0.08
    POSITIVE LOGITS
     hypnot
    0.13
     soothing
    0.12
     hypnosis
    0.12
     distracting
    0.10
     inducing
    0.10
     frases
    0.10
    诱
    0.10
     distractions
    0.10
     calmly
    0.09
     slowly
    0.09
    Activations Density 0.018%

    No Known Activations