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. 87965
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    .bits
    -0.09
     Turning
    -0.09
     aerospace
    -0.08
    .Basic
    -0.08
    -storage
    -0.08
     exploits
    -0.08
    .Connection
    -0.08
    .hardware
    -0.08
     Serg
    -0.08
    /storage
    -0.08
    POSITIVE LOGITS
     entregue
    0.08
    =cut
    0.08
     vouchers
    0.07
     proporcion
    0.07
    お願
    0.07
    Voucher
    0.07
     sms
    0.07
     scattered
    0.07
     forne
    0.07
    Pagination
    0.07
    Activations Density 0.060%

    No Known Activations