© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31595
    Prev
    Next
    INDEX
    Explanations

    Plural and singular forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toaster
    -0.09
    攻略
    -0.08
     complexion
    -0.08
     jockey
    -0.08
     Austria
    -0.08
     Christophe
    -0.08
     internal
    -0.08
     Navigator
    -0.08
     preencher
    -0.08
    .internal
    -0.08
    POSITIVE LOGITS
     plural
    0.13
    Plural
    0.13
    _plural
    0.12
    plural
    0.12
     nouns
    0.11
     రూప
    0.10
     grammatical
    0.09
     singular
    0.09
     বাক
    0.09
     plurality
    0.09
    Activations Density 0.011%

    No Known Activations