© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45291
    Prev
    Next
    INDEX
    Explanations

    better

    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
     ridiculously
    -0.08
     obscure
    -0.07
     mở
    -0.07
     unlikely
    -0.07
    ဖ
    -0.07
     headers
    -0.07
    begr
    -0.07
     hätte
    -0.07
    荒
    -0.07
     danh
    -0.07
    POSITIVE LOGITS
     incidencia
    0.10
     häufiger
    0.10
    Preference
    0.09
     empath
    0.09
     gemiddeld
    0.09
     Preference
    0.09
     vaker
    0.09
     tendency
    0.09
     vaak
    0.09
     propensity
    0.09
    Activations Density 0.037%

    No Known Activations