© 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. 64002
    Prev
    Next
    INDEX
    Explanations

    mathematical induction proofs

    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
    精品
    -0.08
     ತ
    -0.08
     жары
    -0.08
     ಉ
    -0.08
     गुर
    -0.07
     Darkness
    -0.07
    倾
    -0.07
    �
    -0.07
     ಟ
    -0.07
    Axis
    -0.07
    POSITIVE LOGITS
     induct
    0.11
     incremental
    0.10
     combin
    0.09
    increment
    0.09
    CREMENT
    0.09
    .patch
    0.09
     Increment
    0.09
    Increment
    0.08
    .increment
    0.08
     increment
    0.08
    Activations Density 0.010%

    No Known Activations