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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13023
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    umik
    -0.09
    _letters
    -0.08
    uming
    -0.08
    øst
    -0.08
    umatic
    -0.08
    atore
    -0.08
    Letters
    -0.08
    ateur
    -0.07
    umuz
    -0.07
    azione
    -0.07
    POSITIVE LOGITS
     Apro
    0.08
     LC
    0.08
     thrust
    0.08
    ********
    0.08
     Avalon
    0.07
     outs
    0.07
    Aval
    0.07
     hy
    0.07
    277
    0.07
    ובה
    0.07
    Activations Density 0.028%

    No Known Activations