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. 42056
    Prev
    Next
    INDEX
    Explanations

    They

    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
     dauern
    -0.08
    Cle
    -0.08
     διάρκεια
    -0.08
     pudd
    -0.08
    lds
    -0.07
     Gly
    -0.07
     tó
    -0.07
    山
    -0.07
    (bp
    -0.07
     ty
    -0.07
    POSITIVE LOGITS
     want
    0.12
     wants
    0.12
     wanting
    0.11
     চান
    0.11
     רוצה
    0.10
     Wants
    0.10
     möchtest
    0.10
     ترغب
    0.10
     хочет
    0.10
     चाहता
    0.09
    Activations Density 0.060%

    No Known Activations