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. 184
    Prev
    Next
    INDEX
    Explanations

    exposure

    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
    QI
    -0.10
     карти
    -0.09
     acidentes
    -0.08
     университет
    -0.08
     Sachs
    -0.08
     liens
    -0.08
     сем
    -0.08
     speculate
    -0.08
    IMA
    -0.08
     proteínas
    -0.08
    POSITIVE LOGITS
     gradual
    0.10
     therapy
    0.09
     gradually
    0.09
     progressively
    0.09
     placebo
    0.09
     العلاج
    0.09
     targeted
    0.08
     علاج
    0.08
     nightmare
    0.08
     fearful
    0.08
    Activations Density 0.007%

    No Known Activations