© 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. 19-RESID-POST-AA
    11. 102538
    Prev
    Next
    INDEX
    Explanations

    init

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ầ
    -0.09
    quetes
    -0.09
    qatigiiff
    -0.09
    icao
    -0.09
     plaatse
    -0.09
    qatigiiss
    -0.09
    qarfiit
    -0.09
    ाष्ट्रिय
    -0.09
    quete
    -0.09
     ఇతర
    -0.09
    POSITIVE LOGITS
     a
    0.10
    __()↵↵
    0.09
     but
    0.09
    __()↵
    0.09
     and
    0.09
     The
    0.08
    .
    0.08
     again
    0.08
    0.08
     different
    0.08
    Activations Density 0.004%

    No Known Activations