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. 113857
    Prev
    Next
    INDEX
    Explanations

    pensions, work history, retirement

    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
     dumb
    -0.08
     kommunik
    -0.08
     темат
    -0.08
     fruta
    -0.08
    .arrow
    -0.08
     bait
    -0.08
    水果
    -0.08
     soothing
    -0.08
     રૂપ
    -0.08
    暗
    -0.07
    POSITIVE LOGITS
    累计
    0.12
     accrued
    0.12
    累
    0.12
    Years
    0.12
     accumulated
    0.11
     histories
    0.11
    _elapsed
    0.11
     tenure
    0.10
    Elapsed
    0.10
    elapsed
    0.10
    Activations Density 0.010%

    No Known Activations