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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 11811
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    etting
    -0.08
     intre
    -0.08
     jud
    -0.07
     trav
    -0.07
     evidently
    -0.07
     area's
    -0.07
     bwe
    -0.07
     unequal
    -0.07
    _j
    -0.07
    .No
    -0.07
    POSITIVE LOGITS
    .fxml
    0.08
     overzicht
    0.08
    Spacer
    0.08
     Spacer
    0.08
     Dough
    0.08
     zichzelf
    0.07
     दोन
    0.07
     जैसा
    0.07
     Übersicht
    0.07
    bewijs
    0.07
    Activations Density 0.009%

    No Known Activations