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. 77951
    Prev
    Next
    INDEX
    Explanations

    background

    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
     MPC
    -0.09
    848
    -0.08
     MSC
    -0.08
     সক্ষম
    -0.08
     mmasị
    -0.08
    �物
    -0.08
    979
    -0.08
    775
    -0.08
     consciously
    -0.07
    uptools
    -0.07
    POSITIVE LOGITS
     literature
    0.08
     beruh
    0.08
     Literature
    0.08
     dienst
    0.07
     smoking
    0.07
     kl
    0.07
     bass
    0.07
     diseases
    0.07
    background
    0.07
    geschichte
    0.07
    Activations Density 0.007%

    No Known Activations