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. 49092
    Prev
    Next
    INDEX
    Explanations

    1

    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
    -0.08
     важно
    -0.08
     governance
    -0.08
    —all
    -0.08
    .attrib
    -0.08
     revolves
    -0.08
    abbat
    -0.08
     government
    -0.07
     duidelijke
    -0.07
    )].
    -0.07
    POSITIVE LOGITS
    _SAN
    0.08
     pinpoint
    0.08
     obtain
    0.08
     Yok
    0.08
     لخوا
    0.08
     তাকে
    0.08
    Splitter
    0.08
     blackout
    0.07
    -photo
    0.07
     ascend
    0.07
    Activations Density 0.004%

    No Known Activations