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. 61141
    Prev
    Next
    INDEX
    Explanations

    cash deals

    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
     mineral
    -0.08
    646
    -0.08
    arina
    -0.08
    321
    -0.07
     paginator
    -0.07
     caster
    -0.07
    ovan
    -0.07
     cyclist
    -0.07
    avin
    -0.07
    510
    -0.07
    POSITIVE LOGITS
    0.08
    资产
    0.08
    եռ
    0.08
    akeup
    0.08
     abduct
    0.08
     toerana
    0.07
     receptor
    0.07
     হয়েছেন
    0.07
    表达
    0.07
     memorable
    0.07
    Activations Density 0.015%

    No Known Activations