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. 119223
    Prev
    Next
    INDEX
    Explanations

    x and y coordinates

    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
     الن
    -0.09
     Nazi
    -0.08
     الإمارات
    -0.07
     repar
    -0.07
     Nash
    -0.07
    by
    -0.07
     atacante
    -0.07
     attacker
    -0.07
     Elon
    -0.07
     Neymar
    -0.07
    POSITIVE LOGITS
     tallest
    0.09
    (rows
    0.09
    مرت
    0.09
    amusoro
    0.09
     estágio
    0.09
     rows
    0.09
    Highest
    0.09
     높
    0.08
    (records
    0.08
     tinggi
    0.08
    Activations Density 0.015%

    No Known Activations