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. 42089
    Prev
    Next
    INDEX
    Explanations

    exponents and negative values

    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
    .cas
    -0.08
    وقة
    -0.08
     personalities
    -0.08
    .blit
    -0.08
    .must
    -0.07
    .v
    -0.07
    .orange
    -0.07
    .dequeue
    -0.07
     driver
    -0.07
     ску
    -0.07
    POSITIVE LOGITS
     invers
    0.08
     posibil
    0.08
    ยา
    0.08
     donnant
    0.08
     cryptocurrencies
    0.08
    akhir
    0.08
     sterling
    0.07
    (currency
    0.07
     inverse
    0.07
    utely
    0.07
    Activations Density 0.020%

    No Known Activations