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. 88107
    Prev
    Next
    INDEX
    Explanations

    period

    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
    Changed
    -0.08
     changed
    -0.07
     CSS
    -0.07
    Css
    -0.07
    _MC
    -0.07
     verwenden
    -0.07
    svc
    -0.07
    Software
    -0.07
     strictly
    -0.07
     olu
    -0.07
    POSITIVE LOGITS
     ardından
    0.10
     પછી
    0.10
     બચ
    0.09
     हाद
    0.09
    事故
    0.09
    ệ
    0.09
     আহত
    0.09
     બાદ
    0.09
     victories
    0.09
     ফলে
    0.08
    Activations Density 0.109%

    No Known Activations