© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 48744
    Prev
    Next
    INDEX
    Explanations

    Encoder

    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
     लिह
    -0.09
     década
    -0.09
    קים
    -0.09
     accru
    -0.08
    760
    -0.08
    .inflate
    -0.08
     दशक
    -0.08
     Conan
    -0.08
     accrued
    -0.08
     comenzó
    -0.08
    POSITIVE LOGITS
     Encoder
    0.10
     encoder
    0.10
     slave
    0.10
     Break
    0.10
     capture
    0.09
    Encoder
    0.09
     ET
    0.09
     Capture
    0.09
    _ET
    0.09
     complementary
    0.09
    Activations Density 0.001%

    No Known Activations