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. 29914
    Prev
    Next
    INDEX
    Explanations

    Calculations and measurements

    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
    Ba
    -0.08
    Ga
    -0.08
    ar
    -0.08
    Ta
    -0.08
    .ga
    -0.08
    _ga
    -0.08
    -er
    -0.07
    (
    -0.07
     microbial
    -0.07
    Gaussian
    -0.07
    POSITIVE LOGITS
     Wow
    0.08
     аэр
    0.08
     특별
    0.08
     એન
    0.07
    oune
    0.07
     Disabilities
    0.07
     Особ
    0.07
     Issue
    0.07
     дорад
    0.07
     Inf
    0.07
    Activations Density 0.481%

    No Known Activations