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. 23448
    Prev
    Next
    INDEX
    Explanations

    &T

    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
     pancakes
    -0.08
     anonymous
    -0.07
     журналі
    -0.07
     plaque
    -0.07
     schak
    -0.07
    油
    -0.07
    �
    -0.07
     plates
    -0.07
     ful
    -0.07
     ilma
    -0.07
    POSITIVE LOGITS
    metro
    0.08
     الأع
    0.08
    омб
    0.08
    plement
    0.08
     Gb
    0.07
     Pulse
    0.07
    0.07
    \P
    0.07
    lichen
    0.07
     ощ
    0.07
    Activations Density 0.008%

    No Known Activations