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. 90106
    Prev
    Next
    INDEX
    Explanations

    AI generated text

    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
     kalah
    -0.08
     مان
    -0.08
    -proof
    -0.08
    slash
    -0.07
    ปอร์ต
    -0.07
    馬
    -0.07
     Gunn
    -0.07
    hasta
    -0.07
    proof
    -0.07
    оприят
    -0.07
    POSITIVE LOGITS
     unusually
    0.09
     atyp
    0.09
     uncommon
    0.09
     unusual
    0.08
     ungewöhn
    0.08
     rdf
    0.08
     Mim
    0.08
     stumbling
    0.08
     sprawling
    0.07
     randomly
    0.07
    Activations Density 0.009%

    No Known Activations