© 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. 1391
    Prev
    Next
    INDEX
    Explanations

    /

    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
    	ti
    -0.08
     nok
    -0.08
     ti
    -0.08
     Insight
    -0.08
     Tf
    -0.08
    _TI
    -0.08
     tard
    -0.08
    inode
    -0.07
     unor
    -0.07
     troch
    -0.07
    POSITIVE LOGITS
    ested
    0.08
    ษ
    0.08
     chines
    0.08
    Slave
    0.08
    Mall
    0.07
     estrange
    0.07
    Worksheet
    0.07
     Slave
    0.07
    ನ್ನು
    0.07
    Supporting
    0.07
    Activations Density 0.013%

    No Known Activations