© 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. 113248
    Prev
    Next
    INDEX
    Explanations

    "U" or "V"

    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
     enlarg
    -0.10
    etse
    -0.08
     enlarge
    -0.08
     enlargement
    -0.08
     male
    -0.08
     SCI
    -0.08
     Il
    -0.07
    _RET
    -0.07
    يت
    -0.07
    male
    -0.07
    POSITIVE LOGITS
     Dedicated
    0.08
     نص
    0.08
     করবেন
    0.08
    Origen
    0.08
    中奖
    0.08
     Insol
    0.08
    .middleware
    0.08
    Dedicated
    0.08
     premiere
    0.08
     dedicated
    0.08
    Activations Density 0.008%

    No Known Activations