© 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. 23-RESID-POST-AA
    6. 96465
    Prev
    Next
    INDEX
    Explanations

    solar panels

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     наркот
    -0.10
     alcool
    -0.10
     لوب
    -0.09
     wrestler
    -0.09
     booze
    -0.09
     fifo
    -0.09
    fifo
    -0.08
     violence
    -0.08
    娱乐场
    -0.08
    邑
    -0.08
    POSITIVE LOGITS
     photovoltaic
    0.29
     zonnepanelen
    0.29
     photovolta
    0.27
     solar
    0.25
     panels
    0.24
     panneaux
    0.24
     PV
    0.23
     zonne
    0.22
     солне
    0.22
     Solar
    0.22
    Activations Density 0.051%

    No Known Activations