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. 77156
    Prev
    Next
    INDEX
    Explanations

    subscribe

    np_max-act · gemini-2.0-flash

    attends to pairs of opening and closing parentheses from content within the parentheses.

    oai_attention-head · gpt-4oTriggered by @mlfinancebook
    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
     gene
    -0.09
     goederen
    -0.07
     mt
    -0.07
     deco
    -0.07
    -0.07
     deg
    -0.07
     Dec
    -0.07
     Matem
    -0.07
     PCR
    -0.07
     Gene
    -0.07
    POSITIVE LOGITS
    provement
    0.09
     poskyt
    0.09
    ❤️
    0.08
     നേടി
    0.08
    Clickable
    0.08
     것도
    0.08
     버튼
    0.08
    estors
    0.08
     obsessed
    0.08
    👍
    0.08
    Activations Density 0.003%

    No Known Activations