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. 43131
    Prev
    Next
    INDEX
    Explanations

    Amazon

    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
     wasa
    -0.09
     designate
    -0.08
    mæ
    -0.08
    wassen
    -0.08
    	sign
    -0.08
     SPORTS
    -0.07
     sere
    -0.07
    	fill
    -0.07
     PROCED
    -0.07
     Sports
    -0.07
    POSITIVE LOGITS
     Kindle
    0.08
     proximity
    0.08
    र्ध
    0.07
    ently
    0.07
     Ebook
    0.07
     torque
    0.07
    上的
    0.07
     продаже
    0.07
     nabij
    0.07
    .fetchall
    0.07
    Activations Density 0.028%

    No Known Activations