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. 15-RESID-POST-AA
    6. 19159
    Prev
    Next
    INDEX
    Explanations

    How many can be made

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    しています
    -0.08
    th
    -0.08
     acknowledged
    -0.07
     जिसने
    -0.07
     acknowledgment
    -0.07
    ि
    -0.07
     acknowled
    -0.07
    ாட்ட
    -0.07
     perceived
    -0.07
    _ack
    -0.07
    POSITIVE LOGITS
     feas
    0.10
     ઉપલબ્ધ
    0.10
     Muqdisho
    0.09
     данной
    0.09
     yeroo
    0.09
     tegelijkertijd
    0.09
     tirer
    0.09
     കഴിയ
    0.09
     obtainable
    0.09
     במסגרת
    0.09
    Activations Density 0.019%

    No Known Activations