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. 112192
    Prev
    Next
    INDEX
    Explanations

    General English text

    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
    。例如
    -0.08
    ombs
    -0.08
    -0.08
    。如果
    -0.07
    。所以
    -0.07
    。因此
    -0.07
    について
    -0.07
    Cum
    -0.07
    Br
    -0.07
    TRACK
    -0.07
    POSITIVE LOGITS
     zwar
    0.16
     samtidigt
    0.10
     certes
    0.10
     nhưng
    0.10
     לבין
    0.10
     sekal
    0.10
     असून
    0.10
    ,同时
    0.10
     ابتدا
    0.09
     mellett
    0.09
    Activations Density 0.281%

    No Known Activations