Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53922
    Prev
    Next
    INDEX
    Explanations

    Business deals and startups

    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
    imestamps
    -0.08
    初始化
    -0.08
     vowels
    -0.08
     hidro
    -0.08
     sobald
    -0.08
     numerator
    -0.08
     Sobald
    -0.08
     vowel
    -0.08
     Locke
    -0.08
    ifficulty
    -0.08
    POSITIVE LOGITS
     attendees
    0.15
     exhibitors
    0.15
     참석
    0.12
     उपस्थित
    0.12
     참가
    0.12
     keynote
    0.12
    现场
    0.11
    endees
    0.11
     asistentes
    0.11
     attendee
    0.11
    Activations Density 0.241%

    No Known Activations