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. 43148
    Prev
    Next
    INDEX
    Explanations

    |

    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
     milestones
    -0.10
     milestone
    -0.08
     welcome
    -0.08
     (€
    -0.07
     infra
    -0.07
    تميز
    -0.07
     monitor
    -0.07
    -0.07
     benchmark
    -0.07
     banque
    -0.07
    POSITIVE LOGITS
     deadly
    0.09
     DEAD
    0.09
     કો�
    0.08
    aggable
    0.08
    .Pod
    0.08
     malicious
    0.08
    :null
    0.08
     နဲ
    0.08
     аммо
    0.08
    curl
    0.08
    Activations Density 0.003%

    No Known Activations