© 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. 94798
    Prev
    Next
    INDEX
    Explanations

    prepositions/articles

    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
     narratives
    -0.07
    宇
    -0.07
    	Simple
    -0.07
     timing
    -0.07
     être
    -0.07
     vital
    -0.07
     Simple
    -0.07
     commodity
    -0.07
     subjects
    -0.07
     humanas
    -0.07
    POSITIVE LOGITS
    Ajax
    0.09
    Buckets
    0.08
    ூக
    0.08
    baka
    0.08
     Sachen
    0.08
     apprécié
    0.08
    ชม
    0.08
    莓
    0.08
     Dere
    0.08
    Arn
    0.07
    Activations Density 0.003%

    No Known Activations