© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96585
    Prev
    Next
    INDEX
    Explanations

    row

    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
     wont
    -0.10
    рд
    -0.09
    олн
    -0.09
    вен
    -0.09
    едлив
    -0.09
     вент
    -0.09
     таким
    -0.09
     сб
    -0.09
    žne
    -0.09
    жет
    -0.09
    POSITIVE LOGITS
    nej
    0.19
    skiej
    0.18
    skiego
    0.15
    nego
    0.15
    ego
    0.14
    kiej
    0.14
    ej
    0.14
    kiego
    0.14
    anej
    0.13
    cji
    0.13
    Activations Density 0.006%

    No Known Activations