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. 12322
    Prev
    Next
    INDEX
    Explanations

    words

    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
     engraved
    -0.09
     transmitted
    -0.08
     transmitting
    -0.08
     (&
    -0.07
     ŝ
    -0.07
    reis
    -0.07
    festival
    -0.07
     expedition
    -0.07
    <{
    -0.07
    antia
    -0.07
    POSITIVE LOGITS
    uangan
    0.08
    ↵↵  ↵
    0.08
     duh
    0.08
     Fifty
    0.08
     yayo
    0.08
    iagn
    0.08
     kterou
    0.08
     proveedor
    0.08
     depan
    0.08
     anga
    0.08
    Activations Density 0.002%

    No Known Activations