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. 43463
    Prev
    Next
    INDEX
    Explanations

    CBT-I (Cognitive Behavioral Therapy)

    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
     جيدة
    -0.08
     YORK
    -0.08
     PUBG
    -0.08
     hugged
    -0.08
    wares
    -0.08
     맡
    -0.08
     minh
    -0.08
     טובה
    -0.07
     flattened
    -0.07
     goed
    -0.07
    POSITIVE LOGITS
     permeability
    0.09
     misconceptions
    0.08
    deen
    0.08
     cells
    0.08
     conditional
    0.08
    	init
    0.08
    conditional
    0.08
     estimating
    0.07
    0.07
     Darcy
    0.07
    Activations Density 0.002%

    No Known Activations