© 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. 2631
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Cous
    -0.09
     Jean
    -0.08
    outer
    -0.07
    uil
    -0.07
    Jean
    -0.07
     fueran
    -0.07
    учу
    -0.07
    ские
    -0.07
     unten
    -0.07
     metropolitan
    -0.07
    POSITIVE LOGITS
    Hmm
    0.09
     abr
    0.08
    zx
    0.08
     Prud
    0.08
    Parad
    0.08
     paradise
    0.08
     Yol
    0.08
     Meridian
    0.08
     Montgomery
    0.08
    Abr
    0.07
    Activations Density 0.033%

    No Known Activations