© 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 EvalsExportsinterp-engineNEWAPI 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. 50963
    Prev
    Next
    INDEX
    Explanations

    安

    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
    áték
    -0.08
    apele
    -0.08
     avenue
    -0.08
     paradise
    -0.07
    hal
    -0.07
    -array
    -0.07
    անի
    -0.07
    thread
    -0.07
    -0.06
     tomando
    -0.06
    POSITIVE LOGITS
    赖
    0.11
    �
    0.09
    歉
    0.09
    ве
    0.09
    ρει
    0.08
    vuld
    0.08
    CLU
    0.08
    циям
    0.08
    置
    0.08
    entious
    0.08
    Activations Density 0.007%
    No Known Activations