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. 120115
    Prev
    Next
    INDEX
    Explanations

    stack

    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
     Whitening
    -0.10
     crédit
    -0.09
     cerveau
    -0.09
     applause
    -0.08
     उद्देश्य
    -0.08
     booklet
    -0.08
     lodging
    -0.08
     lumps
    -0.08
     pah
    -0.08
    823
    -0.08
    POSITIVE LOGITS
     ಪರಿಣ
    0.09
     expertise
    0.09
     услуги
    0.09
    担当
    0.08
     technologies
    0.08
    architect
    0.08
     servicios
    0.08
     infra
    0.08
     разработки
    0.08
     tecnologías
    0.08
    Activations Density 0.025%

    No Known Activations