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. 77465
    Prev
    Next
    INDEX
    Explanations

    close games

    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
     дир
    -0.08
     orientar
    -0.08
    -0.08
     sym
    -0.08
     cabin
    -0.07
     поч
    -0.07
     प्रकाश
    -0.07
     Berl
    -0.07
     bilden
    -0.07
    venir
    -0.07
    POSITIVE LOGITS
     spannend
    0.11
    競
    0.09
     enjeux
    0.09
     disput
    0.09
    竞争
    0.09
     hals
    0.09
     borderline
    0.09
     enje
    0.08
     intric
    0.08
    balanced
    0.08
    Activations Density 0.041%

    No Known Activations