© 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. 763
    Prev
    Next
    INDEX
    Explanations

    outer

    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
     Angehör
    -0.08
     Mit
    -0.08
     Dos
    -0.08
    override
    -0.07
     dosage
    -0.07
     upbeat
    -0.07
     Intens
    -0.07
     brothers
    -0.07
    Dos
    -0.07
     enrich
    -0.07
    POSITIVE LOGITS
    ドラ
    0.09
     puppy
    0.09
     flap
    0.08
     ഒഴ
    0.08
     vro
    0.08
     рисун
    0.08
     moat
    0.08
     отверст
    0.07
     moj
    0.07
     courtyard
    0.07
    Activations Density 0.006%

    No Known Activations