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. 117440
    Prev
    Next
    INDEX
    Explanations

    aromatization

    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
     Sci
    -0.09
    Moder
    -0.08
    uvre
    -0.07
     Panda
    -0.07
     Meanwhile
    -0.07
    Police
    -0.07
     meanwhile
    -0.07
    Meanwhile
    -0.07
    schung
    -0.07
    geois
    -0.07
    POSITIVE LOGITS
     painstaking
    0.09
     voorz
    0.09
     değildir
    0.08
     razor
    0.08
     없는
    0.08
     아닌
    0.08
     dayan
    0.08
    ليات
    0.08
     باسم
    0.07
     καλύτε
    0.07
    Activations Density 0.001%

    No Known Activations