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. 46837
    Prev
    Next
    INDEX
    Explanations

    golden hour

    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
     sobe
    -0.08
     Disposable
    -0.08
     disposable
    -0.08
     choices
    -0.07
     facts
    -0.07
     servic
    -0.07
     modular
    -0.07
    mechan
    -0.07
     nomor
    -0.07
     strategies
    -0.07
    POSITIVE LOGITS
    皮
    0.10
     кист
    0.10
     зел
    0.09
     foliage
    0.09
     afternoon
    0.09
     ziel
    0.09
     morning
    0.09
    午後
    0.09
    .grey
    0.08
    霞
    0.08
    Activations Density 0.017%

    No Known Activations