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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 42126
    Prev
    Next
    INDEX
    Explanations

    Numbers and identifiers

    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
     proceder
    -0.08
     unul
    -0.08
     unloading
    -0.08
    реж
    -0.08
    urllib
    -0.07
     diversi
    -0.07
     charismatic
    -0.07
     склада
    -0.07
     เข
    -0.07
    uis
    -0.07
    POSITIVE LOGITS
     செய
    0.08
     Knight
    0.07
    .learn
    0.07
    ုပ်
    0.07
    endum
    0.07
     Collision
    0.07
     செல
    0.07
     Andrade
    0.07
     Ix
    0.07
    _as
    0.07
    Activations Density 2.732%

    No Known Activations