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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 75404
    Prev
    Next
    INDEX
    Explanations

    b

    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
    oretical
    -0.08
     Financ
    -0.08
    zc
    -0.08
    trä
    -0.08
    أنا
    -0.07
    argest
    -0.07
     Finanzierung
    -0.07
     aqueous
    -0.07
    vermogen
    -0.07
     Europa
    -0.07
    POSITIVE LOGITS
    /comment
    0.08
    Upgradeable
    0.08
     Rik
    0.08
    ONLY
    0.08
    Stamped
    0.08
     магазина
    0.08
     storing
    0.08
     filt
    0.07
     sklad
    0.07
     магаз
    0.07
    Activations Density 0.001%

    No Known Activations