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. 113024
    Prev
    Next
    INDEX
    Explanations

    vectors and math

    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
     linguistic
    -0.08
    ್ಲ
    -0.08
    ర్
    -0.07
    alliative
    -0.07
    Range
    -0.07
     clientèle
    -0.07
    Regular
    -0.07
    _PLATFORM
    -0.07
     demands
    -0.07
    Client
    -0.07
    POSITIVE LOGITS
     OD
    0.09
     enqueue
    0.08
     நே
    0.08
     swimmer
    0.08
     EFI
    0.08
     PTO
    0.08
     STOCK
    0.08
    :NO
    0.08
     Inf
    0.08
     края
    0.08
    Activations Density 0.011%

    No Known Activations