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. 60973
    Prev
    Next
    INDEX
    Explanations

    timers countdowns

    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
     Darcy
    -0.09
     adul
    -0.09
     scandal
    -0.08
     ocasi
    -0.08
    .linkedin
    -0.08
    .springframework
    -0.08
    .loads
    -0.08
     wrongdoing
    -0.08
     produire
    -0.08
    .telegram
    -0.08
    POSITIVE LOGITS
     countdown
    0.25
     Countdown
    0.24
    Countdown
    0.22
     timer
    0.14
    _timer
    0.14
    timer
    0.13
     ticking
    0.13
     timers
    0.13
     decrement
    0.13
    Timer
    0.13
    Activations Density 0.016%

    No Known Activations