Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19191
    Prev
    Next
    INDEX
    Explanations

    for

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parameters
    -0.09
     pertin
    -0.08
     relevantes
    -0.08
    ,有
    -0.08
    xim
    -0.08
    ayon
    -0.08
    umably
    -0.08
    qata
    -0.08
    vr
    -0.08
    iv
    -0.07
    POSITIVE LOGITS
     хотите
    0.10
     wish
    0.09
     تريد
    0.09
     կամ
    0.09
     desej
    0.08
     ձեր
    0.08
     souhaitez
    0.08
     چاہتے
    0.08
     deseas
    0.08
     သ
    0.08
    Activations Density 0.009%

    No Known Activations