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. 88232
    Prev
    Next
    INDEX
    Explanations

    emergencies and evacuation

    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
     enctype
    -0.08
     mana
    -0.08
     бак
    -0.08
    Unary
    -0.08
     nib
    -0.08
     achtergrond
    -0.07
     PHP
    -0.07
     patches
    -0.07
    Nib
    -0.07
     Cah
    -0.07
    POSITIVE LOGITS
     evacuation
    0.17
     evacu
    0.16
    消防
    0.15
     flee
    0.14
     evac
    0.13
     emergency
    0.12
     Feuerwehr
    0.12
    逃
    0.11
     пожар
    0.11
     эв
    0.11
    Activations Density 0.046%

    No Known Activations