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. 119327
    Prev
    Next
    INDEX
    Explanations

    shape

    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
    ارا
    -0.09
     gekopp
    -0.08
     associado
    -0.08
     ڈال
    -0.08
    };
    -0.08
    _SCOPE
    -0.08
    /comments
    -0.08
     AT
    -0.08
    ieres
    -0.08
     Sänger
    -0.08
    POSITIVE LOGITS
    Width
    0.09
     segments
    0.09
     leaf
    0.09
    面积
    0.08
     leaflet
    0.08
     công
    0.08
     width
    0.08
     halves
    0.08
     rectangles
    0.08
     twig
    0.08
    Activations Density 0.027%

    No Known Activations