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. 43768
    Prev
    Next
    INDEX
    Explanations

    like

    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
     Chief
    -0.09
     근
    -0.09
     Bab
    -0.08
     Moll
    -0.08
     Reach
    -0.08
    gänge
    -0.07
     verfügbar
    -0.07
     Mahl
    -0.07
    Chief
    -0.07
     cran
    -0.07
    POSITIVE LOGITS
     iso
    0.08
    /un
    0.08
    KEY
    0.08
    鉴
    0.07
     Austin
    0.07
    ILO
    0.07
     conj
    0.07
    👍
    0.07
     hed
    0.07
     gros
    0.07
    Activations Density 0.038%

    No Known Activations