© 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. 7950
    Prev
    Next
    INDEX
    Explanations

    over

    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
     tun
    -0.08
    àr
    -0.07
     polarization
    -0.07
    regar
    -0.07
     anne
    -0.07
    وسف
    -0.07
    생활
    -0.07
    ğinde
    -0.07
     Anne
    -0.07
    .tab
    -0.07
    POSITIVE LOGITS
     Pit
    0.08
     Leg
    0.08
    -the
    0.08
    glass
    0.08
    zeuge
    0.08
     interc
    0.07
     footprint
    0.07
    隔
    0.07
     hinweg
    0.07
    ייך
    0.07
    Activations Density 0.110%

    No Known Activations