Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2435
    Prev
    Next
    INDEX
    Explanations

    German

    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
     Equip
    -0.08
     hae
    -0.08
    quarters
    -0.07
    Equip
    -0.07
    ampus
    -0.07
     konnte
    -0.07
    ambient
    -0.07
     चौ
    -0.07
    gene
    -0.07
    Oops
    -0.07
    POSITIVE LOGITS
     ול
    0.10
    多年
    0.09
     ולה
    0.08
     wh
    0.08
     gan
    0.08
    高速
    0.08
    方案
    0.08
     laver
    0.07
     �
    0.07
    ել
    0.07
    Activations Density 0.007%

    No Known Activations