© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    Ins

    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
    �
    -0.08
     Tus
    -0.08
     ow
    -0.08
     cob
    -0.07
    全国
    -0.07
    td
    -0.07
    ardige
    -0.07
    (Note
    -0.07
     opst
    -0.07
     nul
    -0.07
    POSITIVE LOGITS
     बाब
    0.08
     Alejandro
    0.08
    icators
    0.07
     wedge
    0.07
     ins
    0.07
     Ai
    0.07
    кара
    0.07
    jt
    0.07
     эксперт
    0.07
    十分
    0.07
    Activations Density 0.012%

    No Known Activations