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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58096
    Prev
    Next
    INDEX
    Explanations

    eq

    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
     כ
    -0.09
     Vista
    -0.08
     göre
    -0.08
     USP
    -0.08
     ਕ
    -0.08
     teht
    -0.08
    ​រ�
    -0.08
     iscr
    -0.08
     þegar
    -0.07
    _che
    -0.07
    POSITIVE LOGITS
    OVED
    0.09
    ******↵
    0.08
    Overs
    0.08
     overs
    0.07
    олня
    0.07
     prolong
    0.07
     overshadow
    0.07
     bearing
    0.07
    њ
    0.07
     pageable
    0.07
    Activations Density 0.002%

    No Known Activations