© 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. 22497
    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
     Cotton
    -0.08
     rye
    -0.08
     Zusammen
    -0.08
    任务
    -0.08
     torsdag
    -0.08
    ခဲ့
    -0.08
     männer
    -0.07
    .scalar
    -0.07
     männ
    -0.07
     rigorous
    -0.07
    POSITIVE LOGITS
     floating
    0.16
    floating
    0.15
    Floating
    0.14
     doubles
    0.13
     floats
    0.13
     Floating
    0.12
    浮
    0.12
    _DOUBLE
    0.11
     double
    0.11
     Double
    0.11
    Activations Density 0.004%

    No Known Activations