© 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. 19015
    Prev
    Next
    INDEX
    Explanations

    past

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esencia
    -0.08
    actéristiques
    -0.08
    773
    -0.08
    533
    -0.07
    3
    -0.07
    (first
    -0.07
    /basic
    -0.07
     básica
    -0.07
    (database
    -0.07
    (main
    -0.07
    POSITIVE LOGITS
     протяжении
    0.15
     השנים
    0.14
     વર્ષ
    0.13
     বছর
    0.13
     века
    0.13
     isikhathi
    0.13
    岁
    0.12
     хугаца
    0.12
     ವರ್ಷ
    0.12
     muddo
    0.12
    Activations Density 0.015%

    No Known Activations