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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44115
    Prev
    Next
    INDEX
    Explanations

    speed

    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
    Пр
    -0.08
    �
    -0.08
    ((*
    -0.08
    ф
    -0.07
    κέ
    -0.07
    Про
    -0.07
    型
    -0.07
    sans
    -0.07
    icelo
    -0.07
    esser
    -0.07
    POSITIVE LOGITS
     balt
    0.09
    cussions
    0.08
    روح
    0.08
    ków
    0.08
     Endpoint
    0.08
    kých
    0.07
     Full
    0.07
    .urls
    0.07
     Pkw
    0.07
    زور
    0.07
    Activations Density 0.000%

    No Known Activations