© 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. 78480
    Prev
    Next
    INDEX
    Explanations

    ost

    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
     Indonesia
    -0.09
     Assistance
    -0.07
    eps
    -0.07
    性
    -0.07
     assistance
    -0.07
     Paras
    -0.07
     ethers
    -0.07
     Res
    -0.07
    ør
    -0.07
     cứu
    -0.07
    POSITIVE LOGITS
    Yep
    0.09
    Vil
    0.09
    Never
    0.08
     Clint
    0.08
     Yep
    0.08
     Chick
    0.08
     Vad
    0.08
     Spaanse
    0.07
    ----↵
    0.07
    لور
    0.07
    Activations Density 0.000%

    No Known Activations