Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43417
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    336
    -0.07
    日前
    -0.07
    zea
    -0.07
    ")==
    -0.07
    ash
    -0.07
    -0.07
     vas
    -0.07
    pieces
    -0.07
     المر
    -0.07
     કોઇ
    -0.07
    POSITIVE LOGITS
    ർന്ന്
    0.09
     εδώ
    0.09
     �
    0.09
     이제
    0.09
     ഇവിടെ
    0.09
    $conn
    0.08
     attendant
    0.08
     atre
    0.08
     lexical
    0.08
     burada
    0.08
    Activations Density 0.044%

    No Known Activations