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. 130067
    Prev
    Next
    INDEX
    Explanations

    opportunities

    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
     Basilica
    -0.09
     crashed
    -0.08
    cry
    -0.08
    "strings
    -0.08
     Uw
    -0.08
    โล
    -0.07
     casas
    -0.07
     utf
    -0.07
     graden
    -0.07
     diversi
    -0.07
    POSITIVE LOGITS
     मौका
    0.11
     opportunity
    0.09
     exceptionnelle
    0.09
     అవకాశం
    0.09
     Gelegenheit
    0.09
     فرصة
    0.09
     oportunidade
    0.09
     ملاقات
    0.09
     الذهب
    0.09
    નીય
    0.09
    Activations Density 0.024%

    No Known Activations