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. 119305
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
     двиг
    -0.08
     antecedentes
    -0.08
     जाती
    -0.08
    encias
    -0.08
     forhold
    -0.08
     devam
    -0.08
     slated
    -0.07
     ücret
    -0.07
     SOC
    -0.07
     sembr
    -0.07
    POSITIVE LOGITS
     തന്റെ
    0.11
     자신의
    0.10
     தனது
    0.09
     يستطيع
    0.09
     discovers
    0.09
     করেছিলেন
    0.09
     sext
    0.09
     Bob
    0.09
     мог
    0.08
     قام
    0.08
    Activations Density 0.055%

    No Known Activations