© 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. 5724
    Prev
    Next
    INDEX
    Explanations

    German adjectives

    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
    -Jährige
    -0.15
     eigene
    -0.14
    -jährige
    -0.14
     ehemalige
    -0.14
     neue
    -0.14
     bekannte
    -0.14
     politische
    -0.14
     kleine
    -0.14
     starke
    -0.13
     entsprechende
    -0.13
    POSITIVE LOGITS
     neues
    0.20
     tolles
    0.19
     weiteres
    0.19
     interessantes
    0.19
     kleines
    0.19
     schönes
    0.18
     essentielles
    0.18
     anderes
    0.18
     besonderes
    0.17
     gutes
    0.17
    Activations Density 0.022%

    No Known Activations