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

    Neuronpedia

    Jacobian LensNEW
    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. 113380
    Prev
    Next
    INDEX
    Explanations

    with

    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
     characterize
    -0.08
     personnage
    -0.08
    .trans
    -0.07
     parole
    -0.07
     jums
    -0.07
     pad
    -0.07
    Je
    -0.07
    _med
    -0.07
     Sok
    -0.07
    Character
    -0.07
    POSITIVE LOGITS
     арналған
    0.10
     Zug
    0.09
     ober
    0.08
     نم
    0.08
     fopen
    0.08
     ખબર
    0.08
     Header
    0.08
    sto
    0.08
     چاہیے
    0.08
     వెళ్ల
    0.07
    Activations Density 0.083%

    No Known Activations