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. 88064
    Prev
    Next
    INDEX
    Explanations

    icul

    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
     autom
    -0.08
     جعل
    -0.08
     automation
    -0.07
     controle
    -0.07
     Dess
    -0.07
     user
    -0.07
    ynchronized
    -0.07
     control
    -0.07
     fps
    -0.07
    酒
    -0.07
    POSITIVE LOGITS
     ущ
    0.09
     Pipes
    0.09
     tunnels
    0.08
    _irq
    0.08
    илак
    0.08
     misery
    0.08
     causada
    0.08
     Socket
    0.08
     IRQ
    0.08
     allev
    0.08
    Activations Density 0.004%

    No Known Activations