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. 103050
    Prev
    Next
    INDEX
    Explanations

    paper

    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
     수
    -0.09
     المتعلقة
    -0.08
     वित्त
    -0.08
     관련
    -0.08
     welcomed
    -0.08
    financial
    -0.08
     orchestr
    -0.08
    사회
    -0.08
    _salary
    -0.08
     Pleasant
    -0.08
    POSITIVE LOGITS
     rectangular
    0.13
     dough
    0.10
     raspberry
    0.10
     flax
    0.09
     бумаги
    0.09
     rectangle
    0.08
     кус
    0.08
     Raspberry
    0.08
     laminated
    0.08
     checker
    0.08
    Activations Density 0.022%

    No Known Activations