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. 120474
    Prev
    Next
    INDEX
    Explanations

    code, equations

    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
    unterricht
    -0.08
    ygon
    -0.08
     démocratie
    -0.08
    99
    -0.08
    _neighbor
    -0.08
    Neighbor
    -0.08
     televisie
    -0.07
     bekannt
    -0.07
     Neighbor
    -0.07
    (validation
    -0.07
    POSITIVE LOGITS
     combinations
    0.12
     togg
    0.10
     combos
    0.09
     toggle
    0.08
     Enum
    0.08
    toggle
    0.08
     parity
    0.08
     Smok
    0.08
    Toggle
    0.08
     Recom
    0.08
    Activations Density 0.016%

    No Known Activations