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. 11-RESID-POST-AA
    6. 48943
    Prev
    Next
    INDEX
    Explanations

    non-English relative pronouns

    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
     thereby
    -0.08
     Sass
    -0.08
     اند
    -0.07
     Off
    -0.07
     dabei
    -0.07
     přes
    -0.07
     נ
    -0.07
    되고
    -0.07
     enormous
    -0.07
     off
    -0.07
    POSITIVE LOGITS
     aire
    0.07
    kre
    0.07
     assol
    0.07
    abria
    0.07
    雕
    0.07
     patrimônio
    0.07
    FN
    0.07
     madr
    0.07
     कथ
    0.07
     FN
    0.07
    Activations Density 0.009%

    No Known Activations