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. 77924
    Prev
    Next
    INDEX
    Explanations

    Foreign languages, code, mixed English

    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
     उल
    -0.08
    -0.08
    therapy
    -0.08
    maschine
    -0.07
    ethi
    -0.07
    jeta
    -0.07
     Machine
    -0.07
     машина
    -0.07
     inverted
    -0.07
     sauveg
    -0.07
    POSITIVE LOGITS
    0.08
     vorbei
    0.08
     Lille
    0.08
    ান্ড
    0.08
     cca
    0.08
     WAN
    0.07
     siento
    0.07
    _logged
    0.07
    _RC
    0.07
    देश
    0.07
    Activations Density 0.411%

    No Known Activations