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. 13013
    Prev
    Next
    INDEX
    Explanations

    big

    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
    othing
    -0.08
     Bidh
    -0.08
    Jump
    -0.07
    Todo
    -0.07
    Sua
    -0.07
    Producto
    -0.07
     proposta
    -0.07
     calming
    -0.07
    .todo
    -0.07
     questionnaire
    -0.07
    POSITIVE LOGITS
     الذين
    0.10
    	names
    0.10
     CEOs
    0.09
     Heroes
    0.09
     allemaal
    0.09
    _names
    0.09
     Members
    0.09
     heroes
    0.09
     كبار
    0.09
     Names
    0.09
    Activations Density 0.223%

    No Known Activations