© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1267
    Prev
    Next
    INDEX
    Explanations

    food recipes

    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
     decisive
    -0.08
     communicated
    -0.07
    -polit
    -0.07
    PAC
    -0.07
    chw
    -0.07
     quantity
    -0.07
     Instal
    -0.07
    qty
    -0.07
    ಪಟ್ಟ
    -0.07
    SPACE
    -0.07
    POSITIVE LOGITS
     Mandel
    0.09
     fio
    0.09
     turkey
    0.08
     Scoped
    0.08
     mushrooms
    0.08
     Herm
    0.08
     mozzarella
    0.08
     fark
    0.08
     salmon
    0.08
     Style
    0.08
    Activations Density 0.130%

    No Known Activations