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. 11796
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    станов
    -0.08
     løs
    -0.07
     Lie
    -0.07
    ãn
    -0.07
    оду
    -0.07
    об
    -0.07
    lán
    -0.07
    _diag
    -0.07
     במ
    -0.07
     banner
    -0.07
    POSITIVE LOGITS
     SEN
    0.09
    肌
    0.08
     taha
    0.08
     SST
    0.07
     multiplex
    0.07
     συνο
    0.07
     സുര
    0.07
     upgrade
    0.07
    zyg
    0.07
     telemetry
    0.07
    Activations Density 0.002%

    No Known Activations