© 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. 7-RESID-POST-AA
    11. 984
    Prev
    Next
    INDEX
    Explanations

    ejaculation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hug
    -0.08
     fert
    -0.07
     soles
    -0.07
    ün
    -0.07
    	wire
    -0.07
     equities
    -0.07
     кун
    -0.07
     Proces
    -0.07
     EPC
    -0.07
     kernel
    -0.07
    POSITIVE LOGITS
     вести
    0.09
    ters
    0.08
    chselt
    0.08
    ामुळे
    0.08
     fewer
    0.08
    .metadata
    0.08
     неоп
    0.08
    тесь
    0.08
    _pa
    0.07
    spiele
    0.07
    Activations Density 0.003%

    No Known Activations