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. 307
    Prev
    Next
    INDEX
    Explanations

    Chemical substituents

    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
     emiss
    -0.07
    رام
    -0.07
     spa
    -0.07
     length
    -0.07
     κινη
    -0.07
    etl
    -0.07
     taut
    -0.07
    length
    -0.07
    elong
    -0.07
    .refresh
    -0.07
    POSITIVE LOGITS
    ırs
    0.09
     Centro
    0.09
     શહેર
    0.08
     Germans
    0.08
    ideas
    0.08
     중앙
    0.08
     ನಗರ
    0.08
    -top
    0.08
     amendments
    0.08
     lawns
    0.08
    Activations Density 0.002%

    No Known Activations