© 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. 99155
    Prev
    Next
    INDEX
    Explanations

    distance units

    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
     lim
    -0.08
     �
    -0.07
     바라
    -0.07
    ちゃん
    -0.07
    .Visibility
    -0.07
     **)
    -0.07
     Percentage
    -0.07
    Percentage
    -0.07
     ಸಾಧ್ಯ
    -0.07
     마련
    -0.07
    POSITIVE LOGITS
    -hours
    0.09
     gulf
    0.09
     march
    0.09
    Mood
    0.08
     Stunden
    0.08
    Premier
    0.08
    Aer
    0.08
    午夜
    0.08
    dul
    0.08
    -cover
    0.08
    Activations Density 0.016%

    No Known Activations