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. 43451
    Prev
    Next
    INDEX
    Explanations

    ..

    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
    att
    -0.07
    ્યાસ
    -0.07
     मालिक
    -0.07
     ses
    -0.07
    Exper
    -0.07
    很好
    -0.07
    -0.07
    Shake
    -0.07
     ent
    -0.07
    angs
    -0.07
    POSITIVE LOGITS
     hug
    0.08
     Zak
    0.08
     അത
    0.08
     Eugen
    0.07
     Fisk
    0.07
     fluctu
    0.07
     Merc
    0.07
    mute
    0.07
     Aub
    0.07
    σκευ
    0.07
    Activations Density 0.008%

    No Known Activations