© 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. 29567
    Prev
    Next
    INDEX
    Explanations

    university archives

    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
     �
    -0.09
     cities
    -0.09
    resh
    -0.09
     ciudades
    -0.08
     sab
    -0.08
     sabotage
    -0.08
     overhe
    -0.08
     crash
    -0.08
    .Dot
    -0.08
     gossip
    -0.08
    POSITIVE LOGITS
     accession
    0.12
     provenance
    0.12
     doi
    0.10
     DOI
    0.10
     photographs
    0.10
    doi
    0.10
     NOAA
    0.10
     photograph
    0.10
     Catalog
    0.10
     katalog
    0.09
    Activations Density 0.047%

    No Known Activations