Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88192
    Prev
    Next
    INDEX
    Explanations

    steampunk

    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
     tester
    -0.08
    콘
    -0.08
     testen
    -0.08
     disposer
    -0.08
     poser
    -0.07
     conversational
    -0.07
     콘
    -0.07
     사이
    -0.07
    چھ
    -0.07
     Rapids
    -0.07
    POSITIVE LOGITS
    וסט
    0.08
     khăn
    0.08
     áit
    0.08
     Lind
    0.08
     ei
    0.08
    ондо
    0.08
     કાર
    0.08
     कार
    0.07
    ייל
    0.07
    燕
    0.07
    Activations Density 0.003%

    No Known Activations