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. 54053
    Prev
    Next
    INDEX
    Explanations

    sales and percentages

    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
     exib
    -0.07
    Usb
    -0.07
    Feat
    -0.07
     playful
    -0.07
    打印
    -0.07
     acerca
    -0.07
     ofere
    -0.07
     conducive
    -0.07
     foran
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     Newly
    0.12
     cohort
    0.11
    昨日
    0.11
     যারা
    0.11
     cohorts
    0.10
     ежегод
    0.10
     задерж
    0.10
     newly
    0.10
     新生
    0.10
     survives
    0.10
    Activations Density 0.012%

    No Known Activations