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. 113790
    Prev
    Next
    INDEX
    Explanations

    that

    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
    diti
    -0.08
     classmates
    -0.08
    akkat
    -0.07
     Din
    -0.07
     Pu
    -0.07
    agment
    -0.07
     categorized
    -0.07
    Pu
    -0.07
    huur
    -0.07
     Harness
    -0.07
    POSITIVE LOGITS
     вод
    0.09
     implies
    0.09
     مطلب
    0.09
     imply
    0.09
    ,那么
    0.08
     implying
    0.08
     nghĩa
    0.08
     ito
    0.08
    iencia
    0.08
    отерап
    0.08
    Activations Density 0.018%

    No Known Activations