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. 15-RESID-POST-AA
    6. 19483
    Prev
    Next
    INDEX
    Explanations

    cell toxicity

    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
     toilet
    -0.09
    (lib
    -0.09
    (load
    -0.08
     degrees
    -0.08
    ilet
    -0.08
     grados
    -0.08
    _hist
    -0.08
     resistor
    -0.08
    ార్థ
    -0.08
     locomotive
    -0.07
    POSITIVE LOGITS
     apoptosis
    0.11
     habilidad
    0.09
     ATP
    0.09
     হত্যা
    0.09
     mitochondrial
    0.09
     قتل
    0.09
     نقصان
    0.09
    .Cells
    0.08
     ആക്രമ
    0.08
    攻击
    0.08
    Activations Density 0.002%

    No Known Activations