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. 65697
    Prev
    Next
    INDEX
    Explanations

    DNA replication/transcription

    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
    oš
    -0.08
    สัมพันธ์
    -0.08
     butt
    -0.08
     embroidered
    -0.08
     census
    -0.08
     anpil
    -0.07
    .fhir
    -0.07
     jspb
    -0.07
    leece
    -0.07
    ROI
    -0.07
    POSITIVE LOGITS
     irr
    0.09
     قلي
    0.08
     despe
    0.08
    障
    0.08
    readonly
    0.07
     turbul
    0.07
    heading
    0.07
     diffus
    0.07
     prerequisite
    0.07
     unwind
    0.07
    Activations Density 0.001%

    No Known Activations