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. 15-RESID-POST-AA
    6. 18918
    Prev
    Next
    INDEX
    Explanations

    necessarily

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     G
    -0.09
    G
    -0.08
    "G
    -0.08
     Basa
    -0.08
    (G
    -0.08
     Hutch
    -0.08
     Honda
    -0.07
    Honda
    -0.07
     Ż
    -0.07
     exactement
    -0.07
    POSITIVE LOGITS
     допуска
    0.11
    允许
    0.10
     pouvant
    0.10
     akár
    0.10
     podendo
    0.09
     flexibility
    0.09
     mocht
    0.09
     acknowledge
    0.09
     willingness
    0.09
     acknowledges
    0.09
    Activations Density 0.019%

    No Known Activations