© 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. 6471
    Prev
    Next
    INDEX
    Explanations

    Science and news articles

    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
    _Com
    -0.09
     leaning
    -0.08
     Duties
    -0.08
    гө
    -0.08
    енным
    -0.08
    КО
    -0.08
     Hội
    -0.07
     vítima
    -0.07
    обар
    -0.07
     víctima
    -0.07
    POSITIVE LOGITS
     U
    0.15
    /U
    0.14
     UT
    0.14
    -U
    0.13
     UL
    0.13
     UC
    0.13
     UM
    0.13
     UF
    0.13
    UT
    0.13
    	U
    0.12
    Activations Density 0.190%

    No Known Activations