© 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. 2772
    Prev
    Next
    INDEX
    Explanations

    of

    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
     monop
    -0.08
     magn
    -0.08
     hips
    -0.08
    ie
    -0.08
    含
    -0.08
     sac
    -0.07
     indiqu
    -0.07
    appa
    -0.07
     indist
    -0.07
     portions
    -0.07
    POSITIVE LOGITS
    -benar
    0.08
    backup
    0.08
    landing
    0.08
    _touch
    0.07
    -sizing
    0.07
     /\.
    0.07
     respite
    0.07
     backup
    0.07
     אמ
    0.07
     suf
    0.07
    Activations Density 0.012%

    No Known Activations