© 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. 113759
    Prev
    Next
    INDEX
    Explanations

    persistence

    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
     William
    -0.08
    _leaf
    -0.08
     Af
    -0.08
     nuevamente
    -0.08
     swiftly
    -0.07
     anew
    -0.07
    ाजी
    -0.07
    Af
    -0.07
     innovación
    -0.07
     Pierre
    -0.07
    POSITIVE LOGITS
     persists
    0.11
     persistence
    0.09
     lasts
    0.08
    下来
    0.08
     persist
    0.08
     Until
    0.08
    Until
    0.08
     બદલ
    0.08
    .persist
    0.08
     longer
    0.08
    Activations Density 0.013%

    No Known Activations