© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12889
    Prev
    Next
    INDEX
    Explanations

    list

    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
    -guide
    -0.09
    ្ម
    -0.08
     coveted
    -0.08
    Guide
    -0.08
     secondaire
    -0.07
     রাতে
    -0.07
    驾驶
    -0.07
     scorch
    -0.07
    �
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     commas
    0.08
     macam
    0.08
    .tt
    0.07
    .wh
    0.07
     Uniform
    0.07
    0.07
     جمله
    0.07
     habe
    0.07
    spinner
    0.07
     الخ
    0.07
    Activations Density 0.012%
    No Known Activations