© 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. 68117
    Prev
    Next
    INDEX
    Explanations

    Animal cruelty

    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
    支付宝
    -0.08
     substit
    -0.07
     dali
    -0.07
     quest
    -0.07
     shattered
    -0.07
     anchored
    -0.07
    ститу
    -0.07
     dismissed
    -0.07
     IRQ
    -0.07
     loyalty
    -0.07
    POSITIVE LOGITS
     cramped
    0.18
     spacious
    0.15
     overcrow
    0.14
    _conditions
    0.12
    Conditions
    0.11
     Spacious
    0.11
     humane
    0.11
     आराम
    0.10
     roomy
    0.10
    crow
    0.10
    Activations Density 0.045%

    No Known Activations