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. 44082
    Prev
    Next
    INDEX
    Explanations

    measuring time/pulses

    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
     landscape
    -0.09
    Landscape
    -0.08
     landscapes
    -0.08
     Landscape
    -0.08
     DISTINCT
    -0.07
     revoke
    -0.07
     unset
    -0.07
    unset
    -0.07
    .Jpa
    -0.07
     disturbances
    -0.07
    POSITIVE LOGITS
     fren
    0.09
    测速
    0.09
    _timer
    0.09
    atá
    0.09
     Sekunden
    0.09
     Timer
    0.09
    Timer
    0.09
     Тур
    0.09
    _Timer
    0.09
    	timer
    0.08
    Activations Density 0.010%

    No Known Activations