© 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. 18950
    Prev
    Next
    INDEX
    Explanations

    genetics

    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
    ่วม
    -0.08
    _POST
    -0.08
     etc
    -0.08
     wiele
    -0.08
     आदि
    -0.07
     일부
    -0.07
    ...'
    -0.07
     ...…↵
    -0.07
     лим
    -0.07
     लिम
    -0.07
    POSITIVE LOGITS
     oziroma
    0.11
     attractiveness
    0.09
    iend
    0.09
    Omschrijving
    0.09
     surroundings
    0.09
     besitzt
    0.09
     vorhand
    0.09
     surrounding
    0.09
     besitzen
    0.09
     rendelkez
    0.09
    Activations Density 0.000%

    No Known Activations