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. 78702
    Prev
    Next
    INDEX
    Explanations

    progressive web apps

    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
     "=
    -0.09
     auk
    -0.08
     comedy
    -0.08
     comedians
    -0.08
    diag
    -0.08
    hetical
    -0.07
     fscanf
    -0.07
     comedic
    -0.07
     Expr
    -0.07
     offens
    -0.07
    POSITIVE LOGITS
     favicon
    0.10
     Lighthouse
    0.10
    .Manifest
    0.10
    .chrome
    0.10
     SPA
    0.10
    /favicon
    0.10
     сервис
    0.09
     Gutenberg
    0.09
    Firefox
    0.09
     घोष
    0.09
    Activations Density 0.006%

    No Known Activations