© 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. 23-RESID-POST-AA
    11. 49891
    Prev
    Next
    INDEX
    Explanations

    aerobic activity

    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
     chop
    -0.08
     chops
    -0.08
     چی
    -0.08
    iasa
    -0.07
     cooling
    -0.07
    ностях
    -0.07
     pushes
    -0.07
     rö
    -0.07
     moatte
    -0.07
    chy
    -0.07
    POSITIVE LOGITS
    ób
    0.10
     विद
    0.08
    cert
    0.08
    ob
    0.08
     accredited
    0.08
    援
    0.07
    ോബ
    0.07
    Ob
    0.07
    OB
    0.07
    ates
    0.07
    Activations Density 0.000%

    No Known Activations