© 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. 5474
    Prev
    Next
    INDEX
    Explanations

    Cartoon images

    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
    .Ph
    -0.10
     photographie
    -0.10
     fotóg
    -0.10
     prostitution
    -0.10
     fotógrafo
    -0.09
     fotos
    -0.09
     fotografías
    -0.09
     nihil
    -0.09
    .Photo
    -0.09
     Nietzsche
    -0.09
    POSITIVE LOGITS
     cartoon
    0.25
     cute
    0.23
     cheerful
    0.22
     vrol
    0.21
     kawai
    0.21
     Cartoon
    0.21
     whimsical
    0.20
     playful
    0.20
     comic
    0.19
     cartoons
    0.19
    Activations Density 0.061%

    No Known Activations