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. 53116
    Prev
    Next
    INDEX
    Explanations

    Sept

    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
    CRT
    -0.08
    เด
    -0.08
     இல்ல
    -0.07
     البلا
    -0.07
     rumor
    -0.07
     Actually
    -0.07
    ś
    -0.07
     generating
    -0.07
     hoạt
    -0.07
     gö
    -0.07
    POSITIVE LOGITS
     inc
    0.08
     Rioja
    0.08
     Oktober
    0.08
     Robbie
    0.08
     Jem
    0.08
     truths
    0.07
     herz
    0.07
     carr
    0.07
     imam
    0.07
    fst
    0.07
    Activations Density 0.105%

    No Known Activations