© 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. 11-RESID-POST-AA
    11. 95601
    Prev
    Next
    INDEX
    Explanations

    dry climates

    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
     hierover
    -0.07
     Sustain
    -0.07
    auga
    -0.07
     davon
    -0.07
    hoog
    -0.07
     Swim
    -0.07
     ESA
    -0.07
     baino
    -0.07
     feas
    -0.07
    ავი
    -0.07
    POSITIVE LOGITS
    特点
    0.12
     tendencies
    0.09
    特色
    0.08
    空气
    0.08
     kenmerken
    0.07
    规律
    0.07
    _rom
    0.07
    事业
    0.07
     carries
    0.07
    kmale
    0.07
    Activations Density 0.004%

    No Known Activations