© 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. 102935
    Prev
    Next
    INDEX
    Explanations

    to

    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
     America's
    -0.09
     आपकी
    -0.08
     Australia's
    -0.08
     Trump's
    -0.08
     вашим
    -0.08
    enching
    -0.08
     Apple's
    -0.07
     আপনার
    -0.07
     మీ
    -0.07
    /articles
    -0.07
    POSITIVE LOGITS
    =
    0.22
    =\
    0.17
    ="\
    0.16
    ={
    0.16
    =/
    0.16
    ='
    0.16
    =$
    0.16
    =C
    0.15
    ="
    0.15
    =${
    0.15
    Activations Density 0.001%

    No Known Activations