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. 56136
    Prev
    Next
    INDEX
    Explanations

    Math expressions

    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
     Gruppen
    -0.08
    ttes
    -0.08
     recommended
    -0.08
    区别
    -0.08
    ASTIC
    -0.07
    olid
    -0.07
    制服
    -0.07
    淘
    -0.07
     Peacock
    -0.07
     agile
    -0.07
    POSITIVE LOGITS
    -axis
    0.10
     axes
    0.09
     axis
    0.09
     eixo
    0.09
    XAxis
    0.09
     idéale
    0.09
     perg
    0.09
     coastline
    0.08
     Axis
    0.08
     inclination
    0.08
    Activations Density 0.022%

    No Known Activations