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. 109601
    Prev
    Next
    INDEX
    Explanations

    p

    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
     productive
    -0.08
     leased
    -0.08
     barter
    -0.08
     profitable
    -0.08
     облад
    -0.08
     paik
    -0.07
     Borrow
    -0.07
    Borrow
    -0.07
     Cheats
    -0.07
     subsid
    -0.07
    POSITIVE LOGITS
    icans
    0.09
     (>
    0.08
     düşük
    0.08
     exceedingly
    0.08
     probability
    0.08
    ayaa
    0.08
    .href
    0.08
    ?p
    0.08
     torr
    0.08
    _href
    0.08
    Activations Density 0.004%

    No Known Activations