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. 74814
    Prev
    Next
    INDEX
    Explanations

    future time

    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
    督
    -0.07
     ü
    -0.07
    ующ
    -0.07
     wurden
    -0.06
    rob
    -0.06
     sili
    -0.06
    кі
    -0.06
     gil
    -0.06
    Community
    -0.06
     opl
    -0.06
    POSITIVE LOGITS
     realistically
    0.14
     neće
    0.12
     foreseeable
    0.12
    不会
    0.11
     unlikely
    0.11
     voorlopig
    0.10
     ولن
    0.10
    unless
    0.10
     ближай
    0.10
     unless
    0.09
    Activations Density 0.096%

    No Known Activations