Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 43
    Prev
    Next
    INDEX
    Explanations

    Degree or extent words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADDING
    -0.09
     fonts
    -0.09
    如何
    -0.09
     Fonts
    -0.09
     GUILayout
    -0.08
    Harga
    -0.08
     churches
    -0.08
     fechas
    -0.08
    在哪
    -0.08
     JText
    -0.08
    POSITIVE LOGITS
     mixture
    0.12
     predominantly
    0.12
     અત્ય
    0.12
     relatively
    0.11
     semi
    0.11
     मिश्र
    0.11
     شبه
    0.11
     quasi
    0.11
     широкий
    0.10
     high
    0.10
    Activations Density 0.063%

    No Known Activations