© 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. 47581
    Prev
    Next
    INDEX
    Explanations

    incomplete transcriptions

    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
    /Form
    -0.07
     aluminium
    -0.07
     predstavlja
    -0.07
    ණ
    -0.07
    ാര
    -0.07
    Want
    -0.07
    Klik
    -0.07
     almond
    -0.07
    .Form
    -0.07
    ionali
    -0.07
    POSITIVE LOGITS
     lifting
    0.09
     lift
    0.08
     lifts
    0.08
     BOT
    0.07
    _NUMBER
    0.07
     mosaic
    0.07
     reconocimiento
    0.07
    _SYNC
    0.07
     Chancen
    0.07
    _unused
    0.07
    Activations Density 0.000%

    No Known Activations