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. 44183
    Prev
    Next
    INDEX
    Explanations

    rephrasing/rewriting

    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
    Harness
    -0.10
     Todd
    -0.09
     OSHA
    -0.09
     Courtney
    -0.09
    万美元
    -0.09
    Chord
    -0.09
     Lyme
    -0.09
     Harness
    -0.09
     Lowe
    -0.09
    .utility
    -0.08
    POSITIVE LOGITS
     Vietnamese
    0.17
     বাংলা
    0.16
     മലയാള
    0.16
     தமிழ்
    0.15
     한국
    0.15
     باللغة
    0.15
     தமிழ
    0.15
     Arabic
    0.15
    Arabic
    0.14
     ગુજરાતી
    0.14
    Activations Density 0.716%

    No Known Activations