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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 114047
    Prev
    Next
    INDEX
    Explanations

    OpenAI training information

    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
    收益
    -0.08
     chương
    -0.08
     aforementioned
    -0.08
    روش
    -0.07
    LATED
    -0.07
    Worth
    -0.07
    Recovered
    -0.07
     سرچ
    -0.07
    riere
    -0.07
    ROLLER
    -0.07
    POSITIVE LOGITS
     запрещ
    0.08
     hacker
    0.08
    ，第
    0.08
    .control
    0.07
     控
    0.07
    、第
    0.07
     permiss
    0.07
    毒
    0.07
    bedrijven
    0.07
    は禁止
    0.07
    Activations Density 0.221%

    No Known Activations