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. 90792
    Prev
    Next
    INDEX
    Explanations

    debugging and attaching processes

    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
     नियंत्रण
    -0.09
    ево
    -0.08
    ुल
    -0.08
    nie
    -0.07
     leveling
    -0.07
     नियंत्र
    -0.07
     басқар
    -0.07
     Ita
    -0.07
     управления
    -0.07
    Mgmt
    -0.07
    POSITIVE LOGITS
    送りします
    0.08
    'aff
    0.08
    固定
    0.08
     nào
    0.08
    automatic
    0.08
     söker
    0.08
    akus
    0.08
     fixé
    0.08
    fixed
    0.08
    صبح
    0.08
    Activations Density 0.001%

    No Known Activations