© 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. 1358
    Prev
    Next
    INDEX
    Explanations

    reduce

    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
     Universitet
    -0.09
     Doh
    -0.08
    _Get
    -0.08
     Belmont
    -0.08
     upsetting
    -0.08
    (Reg
    -0.08
    loo
    -0.08
    Eso
    -0.08
    -che
    -0.08
     bekommen
    -0.08
    POSITIVE LOGITS
     public
    0.08
    废
    0.07
     wpis
    0.07
     साह
    0.07
     раз
    0.07
     eng
    0.07
     BX
    0.07
     Andrea
    0.07
     brittle
    0.07
     factory
    0.07
    Activations Density 0.000%

    No Known Activations