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. 26677
    Prev
    Next
    INDEX
    Explanations

    point

    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
     luar
    -0.08
    heated
    -0.08
     şekl
    -0.07
     WAN
    -0.07
     Conversely
    -0.07
     Baltic
    -0.07
     enumerable
    -0.07
     anarch
    -0.07
     caregivers
    -0.07
    িনী
    -0.07
    POSITIVE LOGITS
     cusp
    0.08
    点评
    0.07
     schwe
    0.07
    cus
    0.07
    ポイント
    0.07
    ODE
    0.07
    oodi
    0.07
    Point
    0.07
     där
    0.07
     Punto
    0.07
    Activations Density 0.022%

    No Known Activations