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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76037
    Prev
    Next
    INDEX
    Explanations

    v

    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
    才能
    -0.08
    ירים
    -0.08
    ตลาด
    -0.08
     vieill
    -0.08
     বু�
    -0.07
     ballroom
    -0.07
    業
    -0.07
    ,否则
    -0.07
     העת
    -0.07
     crypt
    -0.07
    POSITIVE LOGITS
    tribut
    0.08
     meditation
    0.08
    _spawn
    0.08
    aptop
    0.08
     Preferences
    0.08
    στα
    0.08
     conmigo
    0.08
     Hola
    0.07
     отметить
    0.07
    _limit
    0.07
    Activations Density 0.006%

    No Known Activations