Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53076
    Prev
    Next
    INDEX
    Explanations

    group

    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
    חד
    -0.08
     elä
    -0.08
     psih
    -0.07
    Cri
    -0.07
    Sharp
    -0.07
    Brush
    -0.07
     γε
    -0.07
    穿
    -0.07
    .Root
    -0.07
    bt
    -0.07
    POSITIVE LOGITS
     گروه
    0.11
     nhóm
    0.11
     collaboratively
    0.11
     collaborative
    0.11
     kelompok
    0.11
     teamwork
    0.10
     colabor
    0.09
     grup
    0.09
     groupe
    0.09
     collaborating
    0.09
    Activations Density 0.024%

    No Known Activations