© 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. 23-RESID-POST-AA
    11. 51126
    Prev
    Next
    INDEX
    Explanations

    кож

    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
    appable
    -0.08
    盗
    -0.07
    美
    -0.07
     unstoppable
    -0.07
     apt
    -0.07
     au
    -0.07
     ensuite
    -0.07
    na
    -0.07
    مولة
    -0.07
     BCrypt
    -0.07
    POSITIVE LOGITS
    аном
    0.11
    зам
    0.10
    ан
    0.09
    ура
    0.09
     soul
    0.09
    ух
    0.09
    уру
    0.09
    уха
    0.08
     Soul
    0.08
    iligen
    0.08
    Activations Density 0.000%

    No Known Activations