© 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. 11-RESID-POST-AA
    11. 95590
    Prev
    Next
    INDEX
    Explanations

    screenplays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otyp
    -0.09
    范围
    -0.08
    otypes
    -0.08
    。此外
    -0.08
    opat
    -0.08
     deprivation
    -0.08
     greenhouse
    -0.08
     glycol
    -0.08
     conclusions
    -0.08
    amines
    -0.08
    POSITIVE LOGITS
     şöyle
    0.09
     Begins
    0.09
     unfolds
    0.08
     Prelude
    0.08
     Begin
    0.08
     Here's
    0.08
    //----------------------------------------------------------------
    0.08
     নিচ
    0.08
     Verse
    0.08
    如下
    0.08
    Activations Density 0.038%

    No Known Activations