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. 361
    Prev
    Next
    INDEX
    Explanations

    ban

    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
     entreg
    -0.08
     Gesch
    -0.08
    h
    -0.07
     Germ
    -0.07
    лага
    -0.07
     tenho
    -0.07
    �
    -0.07
     vent
    -0.07
     germ
    -0.07
    درجة
    -0.07
    POSITIVE LOGITS
    fik
    0.08
     pf
    0.07
     workplace
    0.07
    掉
    0.07
     Kemp
    0.07
     администра
    0.07
    AMI
    0.07
     overhaul
    0.07
    -angle
    0.07
    览
    0.07
    Activations Density 0.010%

    No Known Activations