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. 76498
    Prev
    Next
    INDEX
    Explanations

    continue

    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
    _AG
    -0.07
    Migr
    -0.07
     Cru
    -0.07
     Plast
    -0.07
     ’
    -0.07
    Caching
    -0.07
    .Js
    -0.07
    onos
    -0.07
    ്ഞ
    -0.07
    iva
    -0.07
    POSITIVE LOGITS
     ادامه
    0.11
     Verlauf
    0.10
     devam
    0.09
    ubat
    0.09
     vervolg
    0.09
    ताल
    0.09
     continuar
    0.09
     дальше
    0.08
     crescer
    0.08
     આગળ
    0.08
    Activations Density 0.020%

    No Known Activations