© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51327
    Prev
    Next
    INDEX
    Explanations

    Contractions with pronouns

    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
    ೀ
    -0.18
    ুয়ারি
    -0.18
     أيضاً
    -0.17
    ೇ
    -0.17
    ുകള്
    -0.16
    িয়
    -0.16
    ’,
    -0.16
    ികള്
    -0.16
    ’utilisation
    -0.16
    ’।
    -0.15
    POSITIVE LOGITS
    "It's
    0.26
     you're
    0.25
     You'll
    0.24
     you've
    0.24
     she's
    0.24
     They're
    0.24
    it's
    0.24
     She's
    0.24
     you'll
    0.23
     they're
    0.23
    Activations Density 0.317%

    No Known Activations