© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 483
    Prev
    Next
    INDEX
    Explanations

    contract

    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
    ointe
    -0.09
     astro
    -0.08
     Duarte
    -0.08
     Combo
    -0.07
     renom
    -0.07
     мульт
    -0.07
    ollower
    -0.07
     মহিলা
    -0.07
     genoeg
    -0.07
    Storyboard
    -0.07
    POSITIVE LOGITS
     expectativa
    0.09
     covenant
    0.09
     hükü
    0.09
     العلاقة
    0.09
     सरकार
    0.08
     government's
    0.08
    关系
    0.08
     Erwartungen
    0.08
    relationship
    0.08
     relationship
    0.08
    Activations Density 0.011%

    No Known Activations