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. 49050
    Prev
    Next
    INDEX
    Explanations

    colon after "prompt"

    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
     المست
    -0.08
     integración
    -0.07
    integration
    -0.07
     Abra
    -0.07
    .ag
    -0.07
    Periodic
    -0.07
    visions
    -0.07
    .starts
    -0.07
    102
    -0.07
     Trans
    -0.07
    POSITIVE LOGITS
    ちゃ
    0.08
     punctuation
    0.08
     шел
    0.08
     orb
    0.08
     nuanced
    0.08
     допуст
    0.08
     пед
    0.07
     மண
    0.07
     вами
    0.07
     კვ
    0.07
    Activations Density 0.006%

    No Known Activations