© 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. 50151
    Prev
    Next
    INDEX
    Explanations

    Jim

    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
    heet
    -0.09
     ז
    -0.09
     וז
    -0.08
    артф
    -0.08
     ל
    -0.08
     זאת
    -0.08
    יכער
    -0.08
     מיט
    -0.08
    bundet
    -0.08
     otp
    -0.08
    POSITIVE LOGITS
    énez
    0.17
    enez
    0.14
    bo
    0.14
     Jim
    0.12
    Jim
    0.11
     Beam
    0.11
    ena
    0.10
    Beam
    0.10
    ousine
    0.10
    eno
    0.10
    Activations Density 0.003%

    No Known Activations