© 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. 30102
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     Towers
    -0.08
    .Ab
    -0.08
     finest
    -0.08
     towers
    -0.07
     samengesteld
    -0.07
     werfen
    -0.07
     Strike
    -0.07
     finis
    -0.07
     chcia
    -0.07
     behoren
    -0.07
    POSITIVE LOGITS
     importancia
    0.11
    importance
    0.10
     importância
    0.10
     أهمية
    0.09
    Importance
    0.09
     importance
    0.09
     penting
    0.08
    곡
    0.08
     중요
    0.08
    นิยม
    0.08
    Activations Density 0.037%

    No Known Activations