© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2737
    Prev
    Next
    INDEX
    Explanations

    ulterior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keel
    -0.08
     Warsaw
    -0.08
     תורה
    -0.07
     teatr
    -0.07
     multilingual
    -0.07
     kej
    -0.07
    -0.07
     Aşgabat
    -0.07
    raph
    -0.07
     latin
    -0.07
    POSITIVE LOGITS
    हु
    0.07
    Resume
    0.07
    exam
    0.07
     sniff
    0.07
     లేద
    0.07
     youngest
    0.07
    筆
    0.07
     subordin
    0.07
    Firm
    0.07
    岩
    0.07
    Activations Density 0.000%
    No Known Activations