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. 45202
    Prev
    Next
    INDEX
    Explanations

    refereeing

    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
     halinde
    -0.09
     অনুয
    -0.08
    prio
    -0.08
    -producing
    -0.08
    ต่อ
    -0.08
    -shaped
    -0.07
     thousand
    -0.07
     Elementary
    -0.07
    قيم
    -0.07
     შესაბამისად
    -0.07
    POSITIVE LOGITS
     作者
    0.08
    🏻
    0.08
    Rob
    0.08
     lush
    0.07
     While
    0.07
     музык
    0.07
    author
    0.07
     JUN
    0.07
     proprietor
    0.07
     Rob
    0.07
    Activations Density 0.027%

    No Known Activations