© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78473
    Prev
    Next
    INDEX
    Explanations

    Period

    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
     simplified
    -0.09
     modest
    -0.08
     ax
    -0.07
    黎
    -0.07
     ></
    -0.07
     directly
    -0.07
    ?s
    -0.07
    chool
    -0.07
     silhou
    -0.07
     limited
    -0.07
    POSITIVE LOGITS
     äußerst
    0.10
     extremamente
    0.09
     extremadamente
    0.09
     extrêmement
    0.09
     बेहद
    0.08
     함께
    0.08
     unglaublich
    0.08
     Comparable
    0.08
     невероят
    0.08
    ��
    0.08
    Activations Density 0.073%

    No Known Activations