Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 102758
    Prev
    Next
    INDEX
    Explanations

    Teaching assistant

    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
     Integr
    -0.08
     geop
    -0.08
     Estratég
    -0.08
     culturally
    -0.08
     Flam
    -0.08
     Flücht
    -0.08
     Natalie
    -0.08
     Quai
    -0.08
     Venet
    -0.08
     Quero
    -0.08
    POSITIVE LOGITS
    umbn
    0.09
    access
    0.08
     acces
    0.08
    _plain
    0.08
    ungeon
    0.08
    ಾನು
    0.08
     conditioners
    0.08
     slab
    0.08
     conditioning
    0.08
     конди
    0.08
    Activations Density 0.005%

    No Known Activations