© 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. 11-RESID-POST-AA
    11. 68583
    Prev
    Next
    INDEX
    Explanations

    Audio/Video encoding/conversion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     touchdown
    -0.10
    �
    -0.09
     aant
    -0.09
     overturned
    -0.09
     gowns
    -0.09
     blossom
    -0.09
    �
    -0.09
     brightly
    -0.09
     Champions
    -0.09
     vegetables
    -0.08
    POSITIVE LOGITS
     audio
    0.21
    (audio
    0.19
    .audio
    0.19
    audio
    0.19
    .wav
    0.18
     الصوت
    0.18
    Audio
    0.18
    (Audio
    0.17
     Audio
    0.17
    _audio
    0.17
    Activations Density 0.085%

    No Known Activations