© 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. 3-RESID-POST-AA
    11. 2565
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disturbance
    -0.08
     locus
    -0.08
    �
    -0.07
    升
    -0.07
    异
    -0.07
     disturbances
    -0.07
     Soll
    -0.07
     κ
    -0.07
    址
    -0.07
     connectors
    -0.07
    POSITIVE LOGITS
    verlening
    0.10
    เหล
    0.09
    گار
    0.09
    🏼
    0.08
     envers
    0.08
     فراہم
    0.08
     ích
    0.08
    ther
    0.08
    desk
    0.08
     voorzien
    0.08
    Activations Density 0.144%

    No Known Activations