Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76483
    Prev
    Next
    INDEX
    Explanations

    Code delimiters

    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
    LAT
    -0.08
     Bhar
    -0.08
    anc
    -0.08
     ontwerp
    -0.08
    Lu
    -0.08
    意思
    -0.07
     Wu
    -0.07
     Carlton
    -0.07
    stan
    -0.07
     Sath
    -0.07
    POSITIVE LOGITS
     hatta
    0.10
     વગેરે
    0.08
     sogar
    0.08
     downright
    0.08
     기타
    0.08
     आदि
    0.08
     même
    0.08
     amph
    0.08
     coloc
    0.08
    อื่น
    0.08
    Activations Density 0.041%

    No Known Activations