© 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. 95213
    Prev
    Next
    INDEX
    Explanations

    or

    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
    .setup
    -0.08
     ঘটে
    -0.08
    Setup
    -0.07
     verwacht
    -0.07
    ಾಖ
    -0.07
    Specified
    -0.07
    utherland
    -0.07
     organisatie
    -0.07
     expects
    -0.07
    Ignored
    -0.07
    POSITIVE LOGITS
     комбина
    0.12
     combinations
    0.12
     kombin
    0.11
     संय
    0.11
     сочет
    0.11
     combina
    0.11
     Kombination
    0.11
     combinación
    0.11
     combos
    0.11
     комб
    0.10
    Activations Density 0.047%

    No Known Activations