© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7838
    Prev
    Next
    INDEX
    Explanations

    behind

    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
     accounting
    -0.08
     replying
    -0.08
    -0.07
     tails
    -0.07
     conduction
    -0.07
     conducting
    -0.07
    .NULL
    -0.07
     factoring
    -0.07
     websites
    -0.07
    面对
    -0.07
    POSITIVE LOGITS
     gesprochen
    0.09
     راست
    0.09
    Routing
    0.08
    spoken
    0.08
     ప్రవ
    0.08
     Geo
    0.08
     hablado
    0.07
    Entered
    0.07
    พู
    0.07
     εί
    0.07
    Activations Density 0.003%

    No Known Activations