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. 12888
    Prev
    Next
    INDEX
    Explanations

    holding objects

    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
     जारी
    -0.08
    .Thread
    -0.07
     gyak
    -0.07
     acompanhamento
    -0.07
     issuance
    -0.07
    יחות
    -0.07
    (Delete
    -0.07
    行
    -0.07
    ാഥ
    -0.07
     বিষ
    -0.07
    POSITIVE LOGITS
     вмест
    0.09
     lockers
    0.09
     allotted
    0.09
    容量
    0.09
     kapas
    0.09
    Capacity
    0.08
     beds
    0.08
     capaciteit
    0.08
     shelters
    0.08
     interessiert
    0.08
    Activations Density 0.009%

    No Known Activations