© 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. 11-RESID-POST-AA
    11. 91469
    Prev
    Next
    INDEX
    Explanations

    bones and joints

    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
    -prov
    -0.09
     brainstorming
    -0.09
    prov
    -0.08
     GOP
    -0.08
    �
    -0.08
     hacking
    -0.08
     computing
    -0.08
     procrast
    -0.07
     Addison
    -0.07
    073
    -0.07
    POSITIVE LOGITS
     surfaces
    0.09
     Pair
    0.09
     uye
    0.09
     inmobili
    0.08
     superficies
    0.08
     Begegn
    0.08
     cushioning
    0.08
    磨
    0.08
     noses
    0.08
     поверхность
    0.08
    Activations Density 0.008%

    No Known Activations