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. 12284
    Prev
    Next
    INDEX
    Explanations

    ridge

    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
    法人
    -0.08
     modalities
    -0.08
     bagno
    -0.08
    ーション
    -0.08
     entrant
    -0.08
     sø
    -0.07
     নিয়ম
    -0.07
     modalidad
    -0.07
     restroom
    -0.07
     rupa
    -0.07
    POSITIVE LOGITS
    附近
    0.10
    line
    0.10
    崎
    0.09
     Peaks
    0.08
    0.08
    上的
    0.08
    band
    0.08
     breached
    0.08
    bands
    0.07
    顶
    0.07
    Activations Density 0.004%

    No Known Activations