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. 77394
    Prev
    Next
    INDEX
    Explanations

    pizz

    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
    وغ
    -0.07
    .bo
    -0.07
     boilers
    -0.07
    বল
    -0.07
    Ст
    -0.07
     vo
    -0.07
    -0.07
    iit
    -0.07
     Ст
    -0.07
     vial
    -0.07
    POSITIVE LOGITS
     हाल
    0.09
     okun
    0.08
     tarik
    0.08
     curl
    0.08
    fff
    0.08
     müs
    0.08
    Typed
    0.08
     tercih
    0.08
     wired
    0.08
     رسول
    0.08
    Activations Density 0.001%

    No Known Activations