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. 44068
    Prev
    Next
    INDEX
    Explanations

    sip

    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
     पहल
    -0.09
     पहुंच
    -0.08
    shore
    -0.08
    าราง
    -0.08
     לט
    -0.08
     airlines
    -0.07
    iddy
    -0.07
     nabíd
    -0.07
     arque
    -0.07
     offre
    -0.07
    POSITIVE LOGITS
    .generic
    0.08
    며
    0.08
     groceries
    0.08
     пар
    0.08
     Generic
    0.08
     воду
    0.08
     generic
    0.08
     Empfang
    0.08
     чуж
    0.07
    咖
    0.07
    Activations Density 0.010%

    No Known Activations