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. 52917
    Prev
    Next
    INDEX
    Explanations

    DMA

    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
     pores
    -0.09
    窝
    -0.08
     clubhouse
    -0.08
     passport
    -0.08
    alış
    -0.08
     shelter
    -0.08
    拓
    -0.08
     unfolds
    -0.08
     penetrate
    -0.08
    averse
    -0.08
    POSITIVE LOGITS
     IRQ
    0.09
     الكهرب
    0.08
     vibration
    0.08
    _MAJOR
    0.08
    irq
    0.08
     combat
    0.08
    0.08
    _irq
    0.08
     batalla
    0.07
     M
    0.07
    Activations Density 0.001%

    No Known Activations