Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129656
    Prev
    Next
    INDEX
    Explanations

    in

    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
     итог
    -0.09
     الدع
    -0.09
     ipa
    -0.08
     सेवन
    -0.08
     دع
    -0.08
     આપવા
    -0.08
     ಅವ
    -0.08
    -slip
    -0.08
     يا
    -0.08
     больше
    -0.08
    POSITIVE LOGITS
     district
    0.12
     town
    0.11
     cities
    0.11
    Germany
    0.10
     China
    0.10
     Italy
    0.10
    Singapore
    0.10
     Australia
    0.10
     Germany
    0.10
     Taiwan
    0.10
    Activations Density 0.226%

    No Known Activations