© 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. 54728
    Prev
    Next
    INDEX
    Explanations

    door

    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
    sciously
    -0.08
     amenazas
    -0.08
    amt
    -0.08
     unab
    -0.08
     tunne
    -0.08
    Annual
    -0.08
    fälle
    -0.08
     amenaza
    -0.08
     contributing
    -0.08
     annual
    -0.07
    POSITIVE LOGITS
     tum
    0.07
    是否
    0.07
     verði
    0.07
     Test
    0.07
    讲
    0.07
     کہیں
    0.07
     Inte
    0.07
    Inte
    0.07
     в
    0.07
     won't
    0.07
    Activations Density 0.001%

    No Known Activations