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. 49353
    Prev
    Next
    INDEX
    Explanations

    escape

    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
     Fen
    -0.08
    اور
    -0.07
    gest
    -0.07
     menstrual
    -0.07
    wide
    -0.07
    Gram
    -0.07
    story
    -0.07
     flatter
    -0.07
     Dora
    -0.07
     GOD
    -0.07
    POSITIVE LOGITS
    充分
    0.09
     செய்யப்பட்ட
    0.09
     herr
    0.08
    冒
    0.08
     됩니다
    0.08
    θυν
    0.08
     definite
    0.08
    elä
    0.08
    字符
    0.07
     edilmiş
    0.07
    Activations Density 0.002%

    No Known Activations