© 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. 65019
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
     aprovech
    -0.08
    DG
    -0.07
     DG
    -0.07
     material
    -0.07
     અમ
    -0.07
    claimer
    -0.07
     વધારો
    -0.07
    296
    -0.07
    દાર
    -0.07
    ociations
    -0.07
    POSITIVE LOGITS
     меч
    0.08
     inhib
    0.08
     izao
    0.08
    هات
    0.08
    asz
    0.08
    Whatsapp
    0.07
     kesel
    0.07
    mızı
    0.07
    /category
    0.07
    lsi
    0.07
    Activations Density 0.073%

    No Known Activations