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. 76526
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Replacement
    -0.09
     Kui
    -0.08
    ્યુ
    -0.08
     Commod
    -0.08
     Sens
    -0.08
     تدو
    -0.08
    સ્ટમ
    -0.07
    än
    -0.07
     unsettling
    -0.07
     Override
    -0.07
    POSITIVE LOGITS
    ayas
    0.09
     nhớ
    0.08
    weg
    0.08
     வாய
    0.07
    xp
    0.07
     sili
    0.07
    MVC
    0.07
     magk
    0.07
     wetlands
    0.07
     removable
    0.07
    Activations Density 0.076%

    No Known Activations