© 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. 29754
    Prev
    Next
    INDEX
    Explanations

    pipe symbol

    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
     Hopper
    -0.09
     metallic
    -0.08
     esser
    -0.08
    .percent
    -0.08
    ίζ
    -0.08
    iorn
    -0.07
    ייע
    -0.07
     Governor
    -0.07
    itekerezo
    -0.07
    .Character
    -0.07
    POSITIVE LOGITS
     confused
    0.07
     ingenuity
    0.07
     notices
    0.07
     treg
    0.07
     extrema
    0.07
     einsch
    0.07
    -TV
    0.07
     brut
    0.07
    城
    0.07
    arl
    0.07
    Activations Density 0.027%

    No Known Activations