© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95184
    Prev
    Next
    INDEX
    Explanations

    Inhale/breathing

    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
    Spam
    -0.07
     world's
    -0.07
     stamp
    -0.07
     flavour
    -0.07
    �
    -0.07
     miasta
    -0.07
    クト
    -0.07
     encycl
    -0.07
    level
    -0.07
     neighbourhood
    -0.07
    POSITIVE LOGITS
     Kaw
    0.08
     Kay
    0.08
     Rack
    0.08
     बत
    0.08
     cheeks
    0.07
     Mayer
    0.07
     नेतृत्व
    0.07
     sensations
    0.07
    Dc
    0.07
     отдых
    0.07
    Activations Density 0.001%

    No Known Activations