© 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. 7-RESID-POST-AA
    11. 1491
    Prev
    Next
    INDEX
    Explanations

    equation solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    准
    -0.09
    消费者
    -0.08
    ち
    -0.08
     huku
    -0.08
     batter
    -0.08
    יין
    -0.08
     Olive
    -0.08
    照
    -0.08
     cite
    -0.08
    曝光
    -0.07
    POSITIVE LOGITS
     Gom
    0.09
    sys
    0.08
     Gon
    0.08
     sys
    0.07
     Mu
    0.07
     Belarus
    0.07
    Sid
    0.07
     Licence
    0.07
     CEP
    0.07
    (sys
    0.07
    Activations Density 0.015%

    No Known Activations