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. 106229
    Prev
    Next
    INDEX
    Explanations

    camera

    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
     wiadomo
    -0.09
     Euchar
    -0.08
    malıdır
    -0.08
     செய்த
    -0.08
    oje
    -0.08
     Sherlock
    -0.07
     Herstellung
    -0.07
    osia
    -0.07
     Fay
    -0.07
     plaus
    -0.07
    POSITIVE LOGITS
    Accessory
    0.09
    DEC
    0.07
    _minor
    0.07
     системой
    0.07
     顺
    0.07
     때문에
    0.07
    (decimal
    0.07
    ermission
    0.07
    	sw
    0.07
    $array
    0.07
    Activations Density 0.002%

    No Known Activations