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. 98192
    Prev
    Next
    INDEX
    Explanations

    french endings

    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
    ерв
    -0.09
    étaire
    -0.08
    ERE
    -0.08
    -config
    -0.08
    erved
    -0.08
    adax
    -0.08
    opy
    -0.08
     integrity
    -0.08
    ELY
    -0.08
    átu
    -0.08
    POSITIVE LOGITS
    issant
    0.26
    issants
    0.25
    issante
    0.24
    issait
    0.24
    issez
    0.24
    issement
    0.23
    issent
    0.21
    issements
    0.21
    isseurs
    0.20
    issons
    0.19
    Activations Density 0.005%

    No Known Activations