© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2868
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     lug
    -0.07
    :is
    -0.07
     stealth
    -0.07
    :f
    -0.07
     �
    -0.07
    _SE
    -0.07
    ikin
    -0.06
     BK
    -0.06
     comport
    -0.06
    POSITIVE LOGITS
     pulp
    0.08
    Thi
    0.08
     Thi
    0.08
     chanting
    0.07
     vehe
    0.07
     Palermo
    0.07
    thi
    0.07
    prima
    0.07
     Liv
    0.07
     Série
    0.07
    Activations Density 0.125%

    No Known Activations