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. 60916
    Prev
    Next
    INDEX
    Explanations

    :]

    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
    Chrome
    -0.08
    信誉
    -0.08
     inox
    -0.08
    Ctl
    -0.08
    hound
    -0.08
    voj
    -0.08
     Lime
    -0.08
     əldə
    -0.08
     Chromebook
    -0.08
     Chrome
    -0.08
    POSITIVE LOGITS
     hence
    0.07
     permutations
    0.07
    /or
    0.07
     brackets
    0.07
     figuring
    0.07
    ൂപ
    0.07
     mechanics
    0.07
     serialization
    0.07
     OMIT
    0.07
     exactly
    0.07
    Activations Density 0.001%

    No Known Activations