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. 119189
    Prev
    Next
    INDEX
    Explanations

    aside

    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
     Abstand
    -0.08
    जो
    -0.08
     biodivers
    -0.07
    _ids
    -0.07
    angaje
    -0.07
     राश
    -0.07
    ाउस
    -0.07
    ाम
    -0.07
     πραγματοποι
    -0.07
    aniro
    -0.07
    POSITIVE LOGITS
    Math
    0.08
     péld
    0.08
     dura
    0.08
    'appelle
    0.08
     luga
    0.07
     használ
    0.07
    .GRAY
    0.07
    ```
    0.07
    lut
    0.07
     проп
    0.07
    Activations Density 0.000%

    No Known Activations