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. 42033
    Prev
    Next
    INDEX
    Explanations

    geometric calculations

    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
     headlines
    -0.08
    tere
    -0.08
     bacon
    -0.08
    VF
    -0.07
    (param
    -0.07
     victory
    -0.07
     ấy
    -0.07
    又
    -0.07
     lends
    -0.07
     headline
    -0.07
    POSITIVE LOGITS
     halfway
    0.14
     midway
    0.14
     midpoint
    0.13
     intermediary
    0.13
     промеж
    0.12
     منتصف
    0.12
     intermediate
    0.12
     মাঝ
    0.12
    Intermediate
    0.11
     Intermediate
    0.11
    Activations Density 0.056%

    No Known Activations