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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98278
    Prev
    Next
    INDEX
    Explanations

    say "pa"

    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
    _AM
    -0.10
    Autos
    -0.10
    Ces
    -0.10
    (Cs
    -0.10
    <Car
    -0.10
    Lg
    -0.10
     AMAZ
    -0.10
    luc
    -0.09
    ·l
    -0.09
     combust
    -0.09
    POSITIVE LOGITS
     pa
    0.18
     ko
    0.16
     pauses
    0.14
     paas
    0.13
     ru
    0.13
     paub
    0.13
     pai
    0.12
    (pa
    0.12
     kuti
    0.12
     रुपए
    0.12
    Activations Density 0.008%

    No Known Activations