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. 11-RESID-POST-AA
    6. 99075
    Prev
    Next
    INDEX
    Explanations

    of

    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
     ambitie
    -0.08
     surt
    -0.08
     testen
    -0.08
    ોર્�
    -0.08
     লক্ষ
    -0.08
     bataille
    -0.08
     personeel
    -0.07
    Analyse
    -0.07
     ná
    -0.07
    ્યુ
    -0.07
    POSITIVE LOGITS
    -fledged
    0.10
    (parent
    0.08
     estad
    0.08
     Farmers
    0.08
     Estad
    0.07
     spokesman
    0.07
    allax
    0.07
     Planet
    0.07
    爸爸
    0.07
    returned
    0.07
    Activations Density 0.008%

    No Known Activations