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. 67883
    Prev
    Next
    INDEX
    Explanations

    Broad discussions and opinions

    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
     Brother
    -0.08
     Daughter
    -0.08
     Dement
    -0.07
    otrans
    -0.07
     jouw
    -0.07
     Hier
    -0.07
    okin
    -0.07
     Regional
    -0.07
     classmates
    -0.07
    quiet
    -0.07
    POSITIVE LOGITS
     betroffen
    0.09
     وحتى
    0.09
     beein
    0.08
     afectar
    0.08
     osv
    0.08
     وغيرها
    0.08
     ಸೇರಿದಂತೆ
    0.08
     afect
    0.08
    _WS
    0.08
     പോലും
    0.08
    Activations Density 0.257%

    No Known Activations