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. 30040
    Prev
    Next
    INDEX
    Explanations

    horror movie titles

    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
    731
    -0.07
    733
    -0.07
    .None
    -0.07
    649
    -0.07
     Finanzierung
    -0.07
     tonic
    -0.07
    942
    -0.07
     deeply
    -0.07
     diagnostics
    -0.07
     सी
    -0.07
    POSITIVE LOGITS
     punish
    0.09
     attire
    0.08
     Goodreads
    0.08
     sın
    0.08
     ibyo
    0.08
    letter
    0.08
     الشهر
    0.08
     pleasure
    0.08
    games
    0.08
     الأعمال
    0.08
    Activations Density 0.001%

    No Known Activations