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. 58452
    Prev
    Next
    INDEX
    Explanations

    Change

    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
     unidentified
    -0.07
    ~-
    -0.07
     untreated
    -0.07
     المنزل
    -0.07
     části
    -0.07
    enuhi
    -0.07
    []{"
    -0.07
     घर
    -0.07
     municipality
    -0.07
    営業
    -0.07
    POSITIVE LOGITS
    λα
    0.08
     tuple
    0.08
     wy
    0.08
    allos
    0.08
     tuples
    0.07
     pasan
    0.07
     passato
    0.07
     γνώ
    0.07
     lucr
    0.07
     passer
    0.07
    Activations Density 0.001%

    No Known Activations