© 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. 1426
    Prev
    Next
    INDEX
    Explanations

    Foreign language text

    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
    _INTERFACE
    -0.08
     bege
    -0.08
     എൻ
    -0.08
    enya
    -0.07
    өз
    -0.07
     siquiera
    -0.07
    ىن
    -0.07
     orð
    -0.07
     Recogn
    -0.07
    adult
    -0.07
    POSITIVE LOGITS
    कार
    0.08
     taxis
    0.08
    Flg
    0.08
    Carn
    0.08
    kite
    0.08
     travelled
    0.08
     recalling
    0.08
    _car
    0.08
     Carn
    0.08
    Styl
    0.07
    Activations Density 0.001%

    No Known Activations