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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12898
    Prev
    Next
    INDEX
    Explanations

    plane crashes

    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
     pacing
    -0.08
     cruelty
    -0.08
    किन
    -0.07
     празднич
    -0.07
    ографии
    -0.07
     Pussy
    -0.07
     greeting
    -0.07
     spaces
    -0.07
     yes
    -0.07
    घर
    -0.07
    POSITIVE LOGITS
    事故
    0.12
     tragic
    0.11
     accidents
    0.11
     disastr
    0.11
     અકસ્માત
    0.10
     acidentes
    0.10
     terjadi
    0.10
     दुर्घ
    0.10
     발생
    0.10
     disastrous
    0.10
    Activations Density 0.038%

    No Known Activations