© 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. 23-RESID-POST-AA
    11. 97437
    Prev
    Next
    INDEX
    Explanations

    `

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assemble
    -0.11
     analyze
    -0.10
     assembling
    -0.10
     constructed
    -0.10
     perform
    -0.10
     concatenate
    -0.09
     utilize
    -0.09
     integrate
    -0.09
     Assemble
    -0.09
     assembled
    -0.09
    POSITIVE LOGITS
    指定
    0.24
     지정
    0.21
     指
    0.18
    告诉
    0.18
     निर्द
    0.18
     పేర్క
    0.17
    设置
    0.17
     设置
    0.16
    给
    0.16
    让
    0.16
    Activations Density 0.043%

    No Known Activations