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. 44980
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     yeniden
    -0.09
     medium
    -0.09
     monopol
    -0.09
     sağlay
    -0.08
    ufacturer
    -0.08
    medium
    -0.08
     IPV
    -0.08
    ecer
    -0.08
     ponovno
    -0.08
     evolucion
    -0.08
    POSITIVE LOGITS
     alarms
    0.08
    STRA
    0.08
    .score
    0.08
     Rad
    0.07
    सा
    0.07
     रम
    0.07
     Alarm
    0.07
     Score
    0.07
     Sid
    0.07
     minimalist
    0.07
    Activations Density 0.001%

    No Known Activations