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. 12592
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    uting
    -0.08
    	bt
    -0.08
     Levy
    -0.08
    elight
    -0.08
    issing
    -0.08
     hare
    -0.08
     objections
    -0.07
    goods
    -0.07
    leva
    -0.07
     Henderson
    -0.07
    POSITIVE LOGITS
     默认
    0.10
    :↵//
    0.09
    默认
    0.09
     uncomment
    0.09
     (`
    0.08
    (default
    0.08
     DEFAULT
    0.08
     mill
    0.08
     predefined
    0.08
    效果
    0.08
    Activations Density 0.027%

    No Known Activations