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. 60958
    Prev
    Next
    INDEX
    Explanations

    grammatical structure

    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
    ਤ
    -0.08
    Seq
    -0.08
    SEQ
    -0.07
     scheme
    -0.07
    scheme
    -0.07
    த
    -0.07
    seq
    -0.07
    η
    -0.07
    STRING
    -0.07
    -et
    -0.07
    POSITIVE LOGITS
     Continental
    0.08
     trato
    0.08
     hierbei
    0.08
    bach
    0.08
    ाके
    0.08
     tandis
    0.07
     kwart
    0.07
     heavily
    0.07
    isciplin
    0.07
     เทคนิค
    0.07
    Activations Density 0.624%

    No Known Activations