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. 74677
    Prev
    Next
    INDEX
    Explanations

    in

    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
     aware
    -0.08
     proponents
    -0.08
    /save
    -0.07
     contrasting
    -0.07
     jõ
    -0.07
     regime
    -0.07
    ę
    -0.07
     reaching
    -0.07
     clause
    -0.07
     regimes
    -0.06
    POSITIVE LOGITS
    anut
    0.08
    processable
    0.08
     glam
    0.08
    .Sp
    0.08
    cendo
    0.08
    jack
    0.08
     ferd
    0.08
     Greetings
    0.08
     Atmospheric
    0.07
     Spice
    0.07
    Activations Density 0.000%

    No Known Activations