© 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. 79040
    Prev
    Next
    INDEX
    Explanations

    question words

    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
     Updating
    -0.08
    LL
    -0.08
     Military
    -0.07
    BAC
    -0.07
    VA
    -0.07
     Approval
    -0.07
    lw
    -0.07
    333
    -0.07
    LD
    -0.07
     Music
    -0.07
    POSITIVE LOGITS
    影响
    0.09
     прояв
    0.09
     ამის
    0.09
    ército
    0.08
     დეკ
    0.08
     exterior
    0.08
    ’extérieur
    0.08
     იან
    0.08
     தெரிவித்துள்ளார்
    0.08
    原因
    0.08
    Activations Density 0.092%

    No Known Activations