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. 60478
    Prev
    Next
    INDEX
    Explanations

    Tools and cleaning supplies

    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
    lumbr
    -0.07
     debes
    -0.07
     бан
    -0.07
    бан
    -0.07
    ियल
    -0.07
     конкрет
    -0.07
    Ban
    -0.07
    hand
    -0.07
     Kuz
    -0.07
    Custom
    -0.07
    POSITIVE LOGITS
     filmi
    0.08
     અથવા
    0.08
     ukuze
    0.08
     સાર
    0.08
     Département
    0.08
     Nih
    0.07
     möglichst
    0.07
     hine
    0.07
    aggable
    0.07
    ాప్
    0.07
    Activations Density 0.080%

    No Known Activations