© 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. 54658
    Prev
    Next
    INDEX
    Explanations

    suits/works

    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
    tingen
    -0.07
     inve
    -0.07
    一级
    -0.07
     recomendable
    -0.07
     erfolgre
    -0.07
    putable
    -0.07
    ting
    -0.07
    زان
    -0.07
    /static
    -0.07
     Redemption
    -0.07
    POSITIVE LOGITS
    是否
    0.09
     akkoord
    0.08
    吗
    0.08
     是否
    0.08
     alvor
    0.08
     oke
    0.08
     Questo
    0.08
     refining
    0.08
     пожалуйста
    0.08
    'om
    0.08
    Activations Density 0.025%

    No Known Activations