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. 53837
    Prev
    Next
    INDEX
    Explanations

    ADX

    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
     сө
    -0.07
    avoid
    -0.07
     cárcel
    -0.07
     eggs
    -0.07
    发行
    -0.07
     NSArray
    -0.07
     pär
    -0.07
     ಪರಿ�
    -0.07
    anoi
    -0.06
     мног
    -0.06
    POSITIVE LOGITS
     yeter
    0.08
     polarized
    0.08
     espes
    0.08
     sacar
    0.08
    ुण
    0.08
     മത
    0.08
     acompañ
    0.08
    obet
    0.08
     الشهر
    0.08
     bruke
    0.07
    Activations Density 0.000%

    No Known Activations