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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23167
    Prev
    Next
    INDEX
    Explanations

    here

    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
    urlaub
    -0.08
     المطلوبة
    -0.08
    ienda
    -0.07
     unterstützen
    -0.07
     Nieder
    -0.07
    alliative
    -0.07
     Zugang
    -0.07
     производства
    -0.07
     কেন্দ্র
    -0.07
     производ
    -0.07
    POSITIVE LOGITS
     serr
    0.08
    ety
    0.08
     esquer
    0.08
    \
    0.08
    ahs
    0.07
     العقد
    0.07
    札
    0.07
    Investor
    0.07
    ▲
    0.07
     binds
    0.07
    Activations Density 0.020%

    No Known Activations