© 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. 23-RESID-POST-AA
    11. 49030
    Prev
    Next
    INDEX
    Explanations

    German texts

    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
     und
    -0.15
    Und
    -0.14
     Und
    -0.11
    und
    -0.11
     Dann
    -0.10
    Den
    -0.10
    -und
    -0.10
    Dann
    -0.10
    Sind
    -0.09
    Dan
    -0.09
    POSITIVE LOGITS
     klassische
    0.15
     vielfält
    0.12
     vielseit
    0.12
     einzigartige
    0.12
     eher
    0.12
     klass
    0.12
     eigen
    0.12
     ungewöhn
    0.11
     traditionelle
    0.11
     struktur
    0.11
    Activations Density 0.032%

    No Known Activations