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. 3-RESID-POST-AA
    6. 1786
    Prev
    Next
    INDEX
    Explanations

    出现

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    คน
    -0.08
    lid
    -0.08
    HU
    -0.07
    हित
    -0.07
     elastic
    -0.07
    ி�
    -0.07
     Highland
    -0.07
     thor
    -0.07
     Bir
    -0.07
     ಓ
    -0.07
    POSITIVE LOGITS
    smöglichkeiten
    0.08
     Ganz
    0.08
     glimps
    0.08
    SPA
    0.08
    IPC
    0.08
    授
    0.08
    0.07
     enters
    0.07
     ap
    0.07
    APL
    0.07
    Activations Density 0.001%

    No Known Activations