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. 119582
    Prev
    Next
    INDEX
    Explanations

    holder

    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
     painting
    -0.08
    opathic
    -0.08
     richness
    -0.08
    Painting
    -0.08
    Depuis
    -0.07
    더
    -0.07
    coverage
    -0.07
    park
    -0.07
    Dataset
    -0.07
     gbas
    -0.07
    POSITIVE LOGITS
     Conveyor
    0.09
     fuer
    0.08
    神器
    0.08
     Rhino
    0.08
     用
    0.08
    .Exp
    0.08
     schlech
    0.08
     Designed
    0.08
    窍
    0.08
    aitu
    0.08
    Activations Density 0.066%

    No Known Activations