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. 90176
    Prev
    Next
    INDEX
    Explanations

    problem

    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
     persoon
    -0.08
     moet
    -0.08
    ель
    -0.08
    _PERSON
    -0.07
    ynet
    -0.07
     diaries
    -0.07
    epis
    -0.07
    陈
    -0.07
     �
    -0.07
     cén
    -0.07
    POSITIVE LOGITS
    lict
    0.08
     whatsoever
    0.08
     Auftrag
    0.08
     PTO
    0.08
     části
    0.07
    0.07
    0.07
     Oro
    0.07
    =>{↵
    0.07
    _threads
    0.07
    Activations Density 0.014%

    No Known Activations