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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29423
    Prev
    Next
    INDEX
    Explanations

    cluster

    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
     vowel
    -0.09
     annoyance
    -0.09
     annoyed
    -0.09
    etchup
    -0.08
    -songwriter
    -0.08
     experimentation
    -0.08
     masturb
    -0.08
     waka
    -0.08
    贴
    -0.08
     pornography
    -0.08
    POSITIVE LOGITS
    (cluster
    0.09
    (Security
    0.09
     malls
    0.09
     bol
    0.08
     magnetic
    0.08
     mahal
    0.08
     tumors
    0.08
     এলাকার
    0.08
     cluster
    0.07
    -region
    0.07
    Activations Density 0.002%

    No Known Activations