© 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. 19-RESID-POST-AA
    11. 102878
    Prev
    Next
    INDEX
    Explanations

    "<!"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.09
     youngest
    -0.08
     to
    -0.08
     highest
    -0.08
     such
    -0.08
     fastest
    -0.07
     nearest
    -0.07
     $\
    -0.07
     longest
    -0.07
     decreasing
    -0.07
    POSITIVE LOGITS
    DOCTYPE
    0.26
    doctype
    0.20
    �览
    0.15
    �pp
    0.14
    0.14
    ــــــــ
    0.13
    �को
    0.13
    ��
    0.13
    0.13
    ��
    0.13
    Activations Density 0.001%
    No Known Activations