© 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. 3-RESID-POST-AA
    11. 12983
    Prev
    Next
    INDEX
    Explanations

    je

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redefine
    -0.07
     Cim
    -0.07
     соответств
    -0.07
    SEX
    -0.07
     soared
    -0.07
     consegu
    -0.07
     lose
    -0.07
     оплаты
    -0.07
    =M
    -0.07
     inscr
    -0.07
    POSITIVE LOGITS
     Ep
    0.08
    Ep
    0.08
    _ep
    0.07
     ಬಳಿ
    0.07
     veget
    0.07
    مای
    0.07
    ولت
    0.07
     hippoc
    0.07
     prak
    0.07
     enterr
    0.07
    Activations Density 0.000%

    No Known Activations