Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19709
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     within
    -0.08
     Once
    -0.07
     
    -0.07
     halve
    -0.07
     Pair
    -0.07
     using
    -0.07
     (
    -0.07
     San
    -0.07
     wrapping
    -0.07
     once
    -0.07
    POSITIVE LOGITS
    IVOS
    0.11
     გადა
    0.10
     მდებ
    0.10
    .offset
    0.10
     حضور
    0.10
     դիր
    0.09
    Дата
    0.09
     აქტ
    0.09
     сырт
    0.09
    adaxwey
    0.09
    Activations Density 0.000%

    No Known Activations