© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 16586
    Prev
    Next
    INDEX
    Explanations

    Specify

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     families
    -0.08
     gaz
    -0.08
     states
    -0.08
    Nag
    -0.07
    Feder
    -0.07
     productivity
    -0.07
     lif
    -0.07
    вается
    -0.07
     it
    -0.07
    Tho
    -0.07
    POSITIVE LOGITS
     특정
    0.11
     Specify
    0.10
     específicos
    0.10
     spécifiques
    0.10
    Specify
    0.10
     spezif
    0.10
     vorgenommen
    0.10
    requested
    0.09
     específicas
    0.08
    指定
    0.08
    Activations Density 0.000%

    No Known Activations