© 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. 69618
    Prev
    Next
    INDEX
    Explanations

    Commas and hyphens

    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
     value
    -0.08
    -global
    -0.08
    影
    -0.08
     robustness
    -0.07
    ,value
    -0.07
    щие
    -0.07
    -memory
    -0.07
     αλλά
    -0.07
    roads
    -0.07
    ồi
    -0.07
    POSITIVE LOGITS
     avoiding
    0.09
    .react
    0.08
    避免
    0.08
    浴
    0.08
     rutin
    0.08
     Goth
    0.08
    avljen
    0.08
     detox
    0.08
     избег
    0.07
    乐
    0.07
    Activations Density 0.005%

    No Known Activations