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. 65113
    Prev
    Next
    INDEX
    Explanations

    cyber

    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
    luğu
    -0.08
     dioc
    -0.08
    luk
    -0.07
    -0.07
     مسلم
    -0.07
     הנת
    -0.07
    child
    -0.07
    Child
    -0.07
    manship
    -0.07
    子的
    -0.07
    POSITIVE LOGITS
    -era
    0.11
    时代
    0.09
    Verse
    0.09
     era
    0.09
    -inspired
    0.09
     वातावरण
    0.09
     stuff
    0.08
    科技
    0.08
    wear
    0.08
     বিশ্বের
    0.08
    Activations Density 0.011%

    No Known Activations