© 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. 19-RESID-POST-AA
    11. 22265
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twin
    -0.09
    Twin
    -0.09
    ‡
    -0.09
    双
    -0.09
     twin
    -0.08
    “双
    -0.08
    double
    -0.08
     双
    -0.08
    雙
    -0.08
    clude
    -0.08
    POSITIVE LOGITS
     cycles
    0.23
     cyc
    0.23
     cycle
    0.21
     cycling
    0.20
    周期
    0.20
    _cycle
    0.19
     cyclic
    0.19
    _cycles
    0.18
    cycles
    0.18
    cycle
    0.18
    Activations Density 0.023%

    No Known Activations