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. 15-RESID-POST-AA
    6. 18927
    Prev
    Next
    INDEX
    Explanations

    patience

    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
    에서는
    -0.09
     Haunted
    -0.09
     SECURITY
    -0.09
     mínimos
    -0.08
    .DATA
    -0.08
     sepak
    -0.08
     Stuttgart
    -0.08
     യു�
    -0.08
    .CONT
    -0.08
    联
    -0.08
    POSITIVE LOGITS
     patience
    0.20
     paciencia
    0.18
     терп
    0.17
     patiently
    0.15
    耐
    0.15
     기다
    0.13
    等待
    0.13
     perseverance
    0.13
     इंत
    0.12
     ждать
    0.12
    Activations Density 0.010%

    No Known Activations