© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16492
    Prev
    Next
    INDEX
    Explanations

    positive/negative polarity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цина
    -0.07
     wildcard
    -0.07
     bài
    -0.07
    िने
    -0.07
    insa
    -0.07
     пасп
    -0.07
     given
    -0.07
     impr
    -0.07
     Es
    -0.07
     Biography
    -0.07
    POSITIVE LOGITS
    Thousands
    0.09
    tle
    0.09
    ngoing
    0.08
    Ainsi
    0.08
     trending
    0.08
    isd
    0.08
    -floating
    0.08
     subtle
    0.08
     aard
    0.08
    Kw
    0.08
    Activations Density 0.009%

    No Known Activations