Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2456
    Prev
    Next
    INDEX
    Explanations

    should

    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
     Len
    -0.08
     کرده
    -0.07
     Ee
    -0.07
    UV
    -0.07
     divis
    -0.07
    ....
    -0.07
     peb
    -0.07
     curtains
    -0.07
    Ee
    -0.07
    beta
    -0.07
    POSITIVE LOGITS
     Wing
    0.08
     Might
    0.08
     someday
    0.08
    Wing
    0.07
     Cathy
    0.07
     serem
    0.07
     Pipeline
    0.07
     embarking
    0.07
    (True
    0.07
     deemed
    0.07
    Activations Density 0.014%

    No Known Activations